README.md

---
title: WhisperTranscript
emoji: 🌖
colorFrom: green
colorTo: indigo
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Transcribing the audio file with Whisper
---

Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

# Audio Transcription with Whisper

This Hugging Face Space uses the `openai/whisper-large-v3` model to transcribe audio files (wav, m4a, mp3).  It handles long audio files gracefully.

## How to Use

1. Upload your audio file or record audio directly in the browser.
2. Click the "Transcribe" button.
3. The transcribed text will be displayed in the textbox below.

## Dependencies

- `transformers`
- `torch`
- `torchaudio`
- `gradio`

## Model

`openai/whisper-large-v3`

## Notes

- This space is designed to handle long audio files.
- The audio is resampled to 16kHz if necessary.
- Error messages are displayed if transcription fails.