model_dialect / README.md
Bgeorge's picture
End of training
e6c0501 verified
|
raw
history blame
2.45 kB
metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: model_dialect
    results: []

model_dialect

This model is a fine-tuned version of facebook/wav2vec2-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8947
  • Accuracy: 0.6975

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 3e-05
  • train_batch_size: 32
  • eval_batch_size: 32
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
6.4185 0.9455 13 1.5833 0.2979
6.3212 1.9636 27 1.5130 0.3118
5.7314 2.9818 41 1.3549 0.4711
5.3036 4.0 55 1.2348 0.5150
4.9932 4.9455 68 1.1989 0.5058
4.5875 5.9636 82 1.1178 0.5704
4.327 6.9818 96 1.0420 0.6443
3.9131 8.0 110 1.0319 0.6282
3.7915 8.9455 123 0.9752 0.6744
3.6121 9.9636 137 0.9379 0.6651
3.4393 10.9818 151 0.9254 0.6928
3.2218 12.0 165 0.9149 0.6767
3.1582 12.9455 178 0.9063 0.6952
2.9563 13.9636 192 0.8947 0.6975
2.9563 14.1818 195 0.8946 0.6975

Framework versions

  • Transformers 4.46.0
  • Pytorch 2.4.0
  • Datasets 3.0.1
  • Tokenizers 0.20.0