{ "metadata": { "total_size": 6696811796 }, "weight_map": { "text_decoder.layers.6.ffn.fc1.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs2.0.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs2.2.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.4.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.11.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.9.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.20.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.8.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.2.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.13.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.1.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.10.cross_attention.k_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.19.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs1.2.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.4.conv_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.7.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.5.conv2.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs1.0.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.3.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.19.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.8.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.11.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.21.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.8.ffn.fc1.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.1.conv1.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs2.2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.4.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.1.conv_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs1.2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.15.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.3.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.0.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.upsampler.1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.5.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.9.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.0.ffn.fc1.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.7.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.3.cross_attention.v_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.19.cross_attention.v_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs1.1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.18.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs2.2.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.upsampler.0.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.4.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs1.1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.13.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.14.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.2.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.4.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.12.ffn.fc1.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.2.conv1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.16.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs1.0.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.cross_attention.k_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "vocoder.speaker_embedding.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.1.cross_attention.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.2.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.22.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.18.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.unit_embedding.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.15.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.0.conv2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.22.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.3.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.15.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.21.cross_attention.v_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs1.2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.6.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.10.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.16.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.4.cross_attention.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.10.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.8.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs1.2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.21.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs2.1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.2.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.ffn.fc1.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.4.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.13.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.6.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.15.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.20.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.19.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.1.ffn.fc2.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.21.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.4.ffn.fc1.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs2.1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs1.2.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs1.1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.2.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.22.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs1.1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.16.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.18.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.20.ffn.fc1.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.3.conv1.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs2.2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.0.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.13.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.15.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.13.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.4.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.10.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs2.1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.21.cross_attention.v_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs2.1.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.1.conv1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.12.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.0.conv1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.23.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs1.1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.9.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.14.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.4.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.16.cross_attention.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.23.ffn.fc2.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs1.2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.5.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.2.conv_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.4.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.0.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.8.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.10.cross_attention.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.16.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.3.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.23.cross_attention.k_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.7.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.1.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.3.conv_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.17.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.22.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.17.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.19.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.4.cross_attention.v_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.0.cross_attention.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.19.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.22.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.6.cross_attention.q_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs2.1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.7.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs2.0.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.1.conv2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.11.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.19.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.cross_attention.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.8.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs2.0.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs1.1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs2.2.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs2.1.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs1.0.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.16.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.16.ffn.fc1.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs1.2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs2.0.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs1.2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.16.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.23.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.dur_predictor.ln2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.6.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.3.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.5.ffn.fc2.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.0.conv_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.21.ffn.fc2.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.8.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs2.1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.17.cross_attention.q_proj.bias": "model-00001-of-00004.safetensors", "vocoder.dur_predictor.conv1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.4.ffn.fc2.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs1.2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.3.conv2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.20.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.7.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.16.cross_attention.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.4.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.5.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.1.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.21.ffn.fc1.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs2.1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.22.ffn.fc2.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs1.0.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.14.ffn.fc2.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs2.2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.17.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs1.0.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.15.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs1.1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.18.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.12.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.6.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.19.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.12.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.conv2.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.11.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.cross_attention.v_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.20.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.14.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.3.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.9.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs1.1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.13.cross_attention.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.17.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.cross_attention.v_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs1.2.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs2.0.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.17.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.7.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.11.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.5.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs1.2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.4.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.ffn.fc1.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs2.0.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.12.ffn.fc2.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs1.0.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs2.2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.15.cross_attention.k_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs2.2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.3.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.22.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.21.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.9.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.12.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs2.1.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.upsampler.1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.12.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.conv_post.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.19.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.12.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.10.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.11.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.22.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.9.cross_attention.v_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs2.1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.7.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.6.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.cross_attention.v_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.12.ffn.fc1.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs2.0.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.17.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.11.cross_attention.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.19.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.10.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.15.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.2.conv2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.5.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.upsampler.0.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs2.0.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.5.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs1.1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.17.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs1.0.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.3.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.13.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs1.2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.6.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.17.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.0.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.21.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.1.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.upsampler.3.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.0.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.1.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.18.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.21.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs1.0.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.4.ffn.fc2.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.18.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.22.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.11.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.16.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.9.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs2.0.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.11.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs2.0.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.0.cross_attention.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.0.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.5.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.11.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.14.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.17.cross_attention.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.13.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.3.conv_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.0.cross_attention.v_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.7.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.13.cross_attention.k_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs1.0.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.22.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.3.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.14.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs1.1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.2.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.conv2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.13.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.9.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.23.cross_attention_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.0.cross_attention.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs1.0.bias": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs2.2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs2.1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.1.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.2.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.7.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.2.conv2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs1.1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.2.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.7.ffn.fc1.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.1.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.13.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.8.cross_attention_layer_norm.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.23.ffn_layer_norm.bias": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.0.ffn.fc2.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs2.2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.5.ffn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.9.ffn.fc1.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.20.ffn.fc2.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.23.self_attn_layer_norm.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.3.cross_attention.q_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.20.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs1.2.weight": "model-00001-of-00004.safetensors", "text_encoder.layers.5.ffn.fc2.bias": "model-00001-of-00004.safetensors", "text_decoder.layers.10.cross_attention.q_proj.bias": "model-00001-of-00004.safetensors", "text_encoder.layers.19.ffn.fc1.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.pos_emb_alpha_char": "model-00001-of-00004.safetensors", "text_encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn_layer_norm.weight": "model-00001-of-00004.safetensors", "text_decoder.layers.17.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.12.ffn.fc2.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.pos_emb_alpha": "model-00002-of-00004.safetensors", "text_decoder.layers.5.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.18.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.3.cross_attention.v_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.4.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.14.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.6.cross_attention.v_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.0.cross_attention_layer_norm.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.2.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs1.1.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.21.ffn.fc1.weight": "model-00002-of-00004.safetensors", "vocoder.dur_predictor.conv1.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.14.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.10.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.4.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.13.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.21.cross_attention_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.18.cross_attention.q_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.7.ffn.fc1.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs1.2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.16.cross_attention.v_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.6.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.17.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.17.ffn.fc1.bias": "model-00002-of-00004.safetensors", "vocoder.dur_predictor.ln1.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.5.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.8.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.4.conv1.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.ln1.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.8.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "vocoder.dur_predictor.conv2.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs2.0.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.17.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs2.0.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.11.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.21.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.0.cross_attention.q_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.23.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.4.cross_attention.k_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.23.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.3.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs1.1.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.5.cross_attention_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.15.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.0.ffn.fc1.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs2.1.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.16.cross_attention.k_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.13.ffn.fc1.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.21.cross_attention.k_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.12.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.5.ffn.fc2.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.2.ffn.fc1.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.5.conv1.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs2.1.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.23.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.10.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.22.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.22.ffn.fc2.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.embed_char.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.18.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.9.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.11.ffn.fc1.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.1.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.0.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.10.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.23.cross_attention.q_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.0.conv_layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.11.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.11.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.13.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.4.cross_attention.q_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.3.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs2.0.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.7.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.21.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.23.cross_attention.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.16.cross_attention.k_proj.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs2.0.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.20.cross_attention_layer_norm.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs1.2.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.ln1.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.18.ffn.fc1.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.6.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.7.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.1.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.19.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.20.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.22.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs1.0.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.13.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.21.cross_attention.q_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.3.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.6.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs1.0.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs1.0.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.12.ffn.fc1.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.5.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.20.cross_attention.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs1.2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.21.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.0.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.4.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.16.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.8.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.23.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.20.cross_attention.k_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.0.conv2.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.15.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.6.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.3.ffn.fc1.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.12.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.22.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.20.ffn.fc1.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.22.cross_attention.v_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.23.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.1.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.14.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.22.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs2.0.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs1.1.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.4.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.5.cross_attention.q_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.20.cross_attention.k_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.23.ffn.fc1.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.5.cross_attention.q_proj.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.upsampler.3.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs1.1.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.9.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.15.cross_attention.v_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.15.ffn.fc1.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.17.cross_attention.k_proj.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs1.2.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.2.ffn.fc1.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.23.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.8.cross_attention.k_proj.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs2.2.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.ln2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.15.cross_attention.q_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.7.cross_attention.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.7.ffn.fc2.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs1.1.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.20.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.1.cross_attention_layer_norm.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs2.1.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.14.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.0.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.7.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.6.cross_attention.out_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.4.ffn.fc1.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.12.ffn.fc1.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs1.0.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.19.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.4.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.15.cross_attention.v_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.4.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.14.cross_attention.out_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.0.cross_attention.q_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.10.ffn.fc1.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.1.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs2.1.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs2.2.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs2.0.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.23.ffn.fc2.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.13.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.9.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.1.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.6.cross_attention.k_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.0.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.14.cross_attention.out_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.8.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.20.cross_attention.v_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.11.cross_attention.k_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.10.cross_attention_layer_norm.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.2.conv_layer_norm.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.ln2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.9.ffn.fc1.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs2.1.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs2.0.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs1.0.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.15.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.1.conv_layer_norm.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.3.ffn.fc1.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs2.2.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "vocoder.dur_predictor.conv2.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.12.ffn.fc2.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs1.1.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.0.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.18.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.16.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.21.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.9.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.10.ffn.fc1.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs1.1.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs2.1.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.8.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.6.ffn.fc1.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.3.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.12.cross_attention_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.23.ffn.fc2.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs2.1.bias": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs2.0.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.9.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs2.2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.6.cross_attention.q_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.3.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.17.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.15.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.13.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.1.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.1.cross_attention.v_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "vocoder.dur_predictor.ln1.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.4.cross_attention.out_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.18.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.6.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs2.0.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.18.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.15.cross_attention.q_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.0.ffn.fc1.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.3.cross_attention.k_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.1.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.2.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.12.cross_attention.v_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.12.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.21.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.3.cross_attention_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.19.cross_attention.q_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.conv1.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.3.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.2.cross_attention.out_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.15.ffn.fc2.weight": "model-00002-of-00004.safetensors", "vocoder.dur_predictor.proj.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.15.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.2.cross_attention.k_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.17.self_attn.out_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.20.ffn.fc2.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.23.cross_attention.v_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs2.0.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.20.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.18.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_decoder.layers.15.ffn_layer_norm.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.4.conv1.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.0.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.0.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", "t2u_model.model.encoder.layers.5.ffn.fc2.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.18.cross_attention.k_proj.bias": "model-00002-of-00004.safetensors", "text_encoder.layers.10.self_attn_layer_norm.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.8.ffn_layer_norm.weight": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs1.0.bias": "model-00002-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn_layer_norm.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.11.self_attn.out_proj.weight": "model-00002-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs2.2.weight": "model-00002-of-00004.safetensors", "text_encoder.layers.5.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", "text_decoder.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", "shared.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.13.cross_attention.v_proj.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs1.1.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.10.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.15.cross_attention.k_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.7.cross_attention.k_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.17.cross_attention.v_proj.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.conv1.weight": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.3.conv2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs1.2.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.16.ffn.fc1.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.14.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.16.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.6.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.5.cross_attention.out_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.7.cross_attention.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.13.cross_attention.out_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.3.ffn.fc1.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.4.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.17.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.3.conv1.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.20.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.18.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs1.1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.19.ffn.fc1.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs2.1.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.11.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.19.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.21.cross_attention.k_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.6.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.22.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.8.ffn.fc1.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs1.2.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs1.2.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.6.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.upsampler.4.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.8.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.11.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.5.ffn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs2.1.weight": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.5.ffn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.7.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs2.0.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs1.0.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs1.2.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs1.1.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.6.ffn.fc2.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.11.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.14.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.17.ffn.fc1.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs1.0.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.22.cross_attention.q_proj.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs1.1.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.11.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.17.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.18.ffn.fc1.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.1.ffn.fc1.bias": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.19.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.18.cross_attention.k_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.22.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.4.ffn.fc1.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.9.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.9.cross_attention.out_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.12.cross_attention.k_proj.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs2.2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.8.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.16.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.2.ffn.fc2.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.20.cross_attention.out_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.3.ffn.fc1.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.22.ffn.fc1.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.13.cross_attention_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.9.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.12.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.16.cross_attention_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.18.ffn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.15.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs1.2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.5.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.23.cross_attention.out_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.14.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.9.cross_attention.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.14.cross_attention.q_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs2.1.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.12.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.0.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.14.cross_attention.v_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.6.ffn.fc1.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.7.cross_attention.v_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.3.cross_attention.q_proj.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs1.1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.15.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs2.2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.20.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.14.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.10.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.20.ffn.fc2.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.11.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs2.1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.23.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.20.cross_attention_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.3.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.1.cross_attention.q_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.18.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.5.conv_layer_norm.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.17.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.8.cross_attention_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.9.cross_attention_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs1.2.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.4.ffn.fc2.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.6.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.17.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.4.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.16.ffn.fc2.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.1.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.13.cross_attention.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.6.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs2.1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.11.ffn.fc1.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.2.ffn.fc2.bias": "model-00003-of-00004.safetensors", "text_decoder.layer_norm.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs2.2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.15.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.14.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.3.ffn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.12.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.18.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.12.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.upsampler.2.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.7.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.8.cross_attention.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.9.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.13.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.14.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs1.0.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.1.cross_attention.v_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.1.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.9.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.18.ffn.fc2.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "vocoder.dur_predictor.proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.11.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.6.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.9.self_attn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.4.ffn_layer_norm.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs1.1.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs2.2.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs2.1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.13.cross_attention.k_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.18.cross_attention.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.15.ffn.fc1.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.4.conv2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.6.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.15.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.19.cross_attention.q_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs1.1.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.16.cross_attention_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.22.cross_attention.k_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.2.cross_attention_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.4.cross_attention.q_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs1.0.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.4.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.13.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.9.cross_attention.k_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs1.0.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.upsampler.2.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs1.1.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.0.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.13.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.3.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.12.ffn_layer_norm.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.4.conv2.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs1.1.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.conv_post.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.13.ffn_layer_norm.bias": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.8.ffn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.3.self_attn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.3.cross_attention.k_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.21.cross_attention.out_proj.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs2.1.bias": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.2.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.5.ffn.fc2.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs1.0.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.10.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.10.ffn.fc2.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs2.0.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.15.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.18.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.17.cross_attention_layer_norm.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.23.ffn_layer_norm.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layer_norm.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs1.0.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.20.self_attn.out_proj.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.9.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.1.ffn_layer_norm.weight": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.12.convs2.2.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs1.0.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.12.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn.out_proj.bias": "model-00003-of-00004.safetensors", "t2u_model.model.decoder.embed_tokens.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.15.ffn.fc2.bias": "model-00003-of-00004.safetensors", "t2u_model.model.encoder.layers.5.ffn.fc1.bias": "model-00003-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs2.0.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.23.ffn.fc1.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.7.cross_attention.out_proj.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.12.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_encoder.layers.19.ffn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.10.ffn.fc2.weight": "model-00003-of-00004.safetensors", "text_decoder.layers.1.ffn.fc1.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.4.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.2.ffn_layer_norm.bias": "model-00003-of-00004.safetensors", "text_decoder.layers.8.cross_attention.v_proj.bias": "model-00003-of-00004.safetensors", "text_encoder.layers.9.ffn.fc2.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.23.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.14.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.14.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs1.2.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.7.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.0.ffn.fc1.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.0.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.7.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.16.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.9.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.duration_predictor.proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs2.1.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.6.ffn.fc2.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.18.ffn.fc2.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.6.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.18.ffn.fc2.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.1.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.7.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs2.1.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs2.2.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs1.2.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.19.ffn.fc1.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.5.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.3.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.3.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.20.cross_attention.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.3.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.12.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.10.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.20.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.7.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.22.ffn.fc1.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.18.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.12.cross_attention.q_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.23.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.12.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.16.ffn.fc1.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs1.1.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.22.ffn.fc1.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.16.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.18.ffn.fc1.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.10.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.10.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.14.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs2.0.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.22.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.0.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs1.0.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.14.cross_attention.v_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs2.0.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.17.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.20.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.15.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.5.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.7.ffn.fc2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.22.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.13.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.14.ffn.fc1.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.13.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.19.cross_attention.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.18.cross_attention_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.12.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.3.ffn.fc2.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.2.ffn.fc1.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.22.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.11.cross_attention.v_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.19.cross_attention.v_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.5.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.23.cross_attention.k_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.17.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.15.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.0.cross_attention.out_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.11.cross_attention_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.16.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.7.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.21.ffn.fc2.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.20.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.7.ffn.fc1.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.21.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs1.0.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.16.ffn.fc2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.23.ffn.fc1.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.11.ffn.fc2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.10.ffn.fc1.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.19.cross_attention.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.23.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.1.cross_attention.k_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.16.ffn.fc1.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.23.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.18.cross_attention.v_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs1.2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.0.ffn.fc2.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.5.conv2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.8.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.14.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.21.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.9.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.8.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.4.cross_attention.out_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.1.conv2.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.1.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.22.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.6.cross_attention.k_proj.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.19.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.23.cross_attention.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.19.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.2.cross_attention.v_proj.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.upsampler.4.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs2.0.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.4.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.17.cross_attention.out_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.11.cross_attention.out_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.17.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs2.0.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs2.2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.11.ffn.fc2.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.13.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.19.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.21.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.1.ffn.fc1.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.2.conv1.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.2.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs1.2.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.5.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.3.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.11.cross_attention.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.11.ffn.fc1.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.5.convs2.0.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.21.cross_attention_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.16.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.5.cross_attention.v_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.17.ffn.fc1.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.10.cross_attention.q_proj.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs2.0.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.6.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.21.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.6.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.13.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.14.cross_attention.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.18.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.22.cross_attention.k_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.conv_pre.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.4.conv_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.14.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.8.cross_attention.k_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.7.cross_attention_layer_norm.bias": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.9.ffn.fc2.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.22.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.1.cross_attention.k_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.11.ffn.fc2.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.14.convs1.0.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.0.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.2.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.14.cross_attention.k_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.8.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.2.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.21.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.17.cross_attention.v_proj.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.0.convs1.1.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.0.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs2.2.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs2.2.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.8.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.20.ffn.fc1.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.2.ffn.fc2.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.conv_pre.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.11.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs2.1.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.3.convs2.2.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.10.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.5.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.16.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.6.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.0.conv1.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs1.0.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.22.cross_attention.out_proj.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.4.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.0.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.9.cross_attention.q_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.19.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.9.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.3.ffn.fc2.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layer_norm.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs2.2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.12.cross_attention.out_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.7.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.23.cross_attention_layer_norm.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.10.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.5.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.18.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs2.2.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.4.convs1.0.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.10.convs1.1.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.14.cross_attention.k_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.15.cross_attention.out_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.1.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.2.convs1.2.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.23.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.7.convs2.1.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.5.conv1.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.1.ffn.fc2.bias": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.1.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.3.cross_attention.out_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.20.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.5.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.5.conv_layer_norm.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs2.2.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.17.self_attn.out_proj.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.4.cross_attention_layer_norm.bias": "model-00004-of-00004.safetensors", "t2u_model.model.decoder.layers.3.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.11.convs2.2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.20.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs1.0.weight": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.5.ffn.fc1.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.15.ffn.fc2.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.3.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.1.self_attn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.21.ffn.fc1.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.18.cross_attention.out_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.15.cross_attention.out_proj.bias": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.4.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.18.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "t2u_model.model.encoder.layers.3.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.23.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.12.cross_attention.q_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.0.self_attn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.9.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.1.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.3.ffn_layer_norm.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.16.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.18.cross_attention.q_proj.weight": "model-00004-of-00004.safetensors", "text_encoder.layers.5.ffn.fc1.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.16.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.2.cross_attention.v_proj.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.10.ffn_layer_norm.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.11.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "vocoder.language_embedding.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.0.ffn.fc2.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.8.convs2.1.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.14.ffn.fc1.weight": "model-00004-of-00004.safetensors", "text_decoder.layers.1.cross_attention.out_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.1.convs1.2.bias": "model-00004-of-00004.safetensors", "vocoder.dur_predictor.ln2.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.8.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.13.convs2.0.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.21.cross_attention.q_proj.weight": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.9.convs1.2.bias": "model-00004-of-00004.safetensors", "text_encoder.layers.14.self_attn.out_proj.bias": "model-00004-of-00004.safetensors", "vocoder.hifi_gan.resblocks.6.convs2.2.bias": "model-00004-of-00004.safetensors", "text_decoder.layers.22.cross_attention_layer_norm.bias": "model-00004-of-00004.safetensors" } }