WhisperX

What is it • Setup • Usage • Multilingual • Python • Contribute • More examples

Made by Max Bain • 🌐 https://www.maxbain.com

Whisper-Based Automatic Speech Recognition (ASR) with improved timestamp accuracy using forced alignment.

What is it 🔎

This repository refines the timestamps of openAI's Whisper model via forced aligment with phoneme-based ASR models (e.g. wav2vec2.0), multilingual use-case.

Whisper is an ASR model developed by OpenAI, trained on a large dataset of diverse audio. Whilst it does produces highly accurate transcriptions, the corresponding timestamps are at the utterance-level, not per word, and can be inaccurate by several seconds.

Phoneme-Based ASR A suite of models finetuned to recognise the smallest unit of speech distinguishing one word from another, e.g. the element p in "tap". A popular example model is wav2vec2.0.

Forced Alignment refers to the process by which orthographic transcriptions are aligned to audio recordings to automatically generate phone level segmentation.

Setup ⚙️

Install this package using

pip install git+https://github.com/m-bain/whisperx.git

You may also need to install ffmpeg, rust etc. Follow openAI instructions here https://github.com/openai/whisper#setup.

Usage 💬 (command line)

English

Run whisper on example segment (using default params)

whisperx examples/sample01.wav

For increased timestamp accuracy, at the cost of higher gpu mem, use bigger models e.g.

whisperx examples/sample01.wav --model large.en --align_model WAV2VEC2_ASR_LARGE_LV60K_960H

Result using WhisperX with forced alignment to wav2vec2.0 large:

sample01.mp4

Compare this to original whisper out the box, where many transcriptions are out of sync:

sample_whisper_og.mov

Other languages

The phoneme ASR alignment model is language-specific, for tested languages these models are automatically picked from torchaudio pipelines or huggingface. Just pass in the --language code, and use the whisper --model large.

Currently default models provided for {en, fr, de, es, it, ja, zh, nl}. If the detected language is not in this list, you need to find a phoneme-based ASR model from huggingface model hub and test it on your data.

E.g. German

whisperx --model large --language de examples/sample_de_01.wav

sample_de_01_vis.mov

Python usage 🐍

import whisperx

device = "cuda" 
audio_file = "audio.mp3"

# transcribe with original whisper
model = whisperx.load_model("large", device)
result = model.transcribe(audio_file)

# load alignment model and metadata
model_a, metadata = whisperx.load_align_model(language_code=result["language"], device=device)

# align whisper output
result_aligned = whisperx.align(result["segments"], model_a, metadata, audio_file, device)

print(result["segments"]) # before alignment

print(result_aligned["segments"]) # after alignment
print(result_aligned["word_segments"]) # after alignment

Limitations ⚠️

Not thoroughly tested, especially for non-english, results may vary -- please post issue to let me know the results on your data
Whisper normalises spoken numbers e.g. "fifty seven" to arabic numerals "57". Need to perform this normalization after alignment, so the phonemes can be aligned. Currently just ignores numbers.
Assumes the initial whisper timestamps are accurate to some degree (within margin of 2 seconds, adjust if needed -- bigger margins more prone to alignment errors)
Hacked this up quite quickly, there might be some errors, please raise an issue if you encounter any.

Contribute 🧑‍🏫

If you are multilingual, a major way you can contribute to this project is to find phoneme models on huggingface (or train your own) and test them on speech for the target language. If the results look good send a merge request and some examples showing its success.

The next major upgrade we are working on is whisper with speaker diarization, so if you have any experience on this please share.

Coming Soon 🗓

[x] ~~Multilingual init~~ done

[x] ~~Subtitle .ass output~~ done

[x] ~~Automatic align model selection based on language detection~~ done

[x] ~~Python usage~~ done

[ ] Incorporating word-level speaker diarization

[ ] Inference speedup with batch processing

Contact 📇

Contact maxbain[at]robots[dot]ox[dot]ac[dot]uk for business things.

Acknowledgements 🙏

Of course, this is mostly just a modification to openAI's whisper. As well as accreditation to this PyTorch tutorial on forced alignment

Citation

If you use this in your research, just cite the repo,

@misc{bain2022whisperx,
  author = {Bain, Max},
  title = {WhisperX},
  year = {2022},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/m-bain/whisperX}},
}

as well as the whisper paper,

@article{radford2022robust,
  title={Robust speech recognition via large-scale weak supervision},
  author={Radford, Alec and Kim, Jong Wook and Xu, Tao and Brockman, Greg and McLeavey, Christine and Sutskever, Ilya},
  journal={arXiv preprint arXiv:2212.04356},
  year={2022}
}

and any alignment model used, e.g. wav2vec2.0.

@article{baevski2020wav2vec,
  title={wav2vec 2.0: A framework for self-supervised learning of speech representations},
  author={Baevski, Alexei and Zhou, Yuhao and Mohamed, Abdelrahman and Auli, Michael},
  journal={Advances in Neural Information Processing Systems},
  volume={33},
  pages={12449--12460},
  year={2020}
}

Algon-33/whisperX_debug