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](https://github.com/openai/whisper), 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](https://huggingface.co/facebook/wav2vec2-large-960h-lv60-self).
**Forced Alignment** refers to the process by which orthographic transcriptions are aligned to audio recordings to automatically generate phone level segmentation.
- Paper drop🎓👨🏫! Please see our [ArxiV preprint](https://arxiv.org/abs/2303.00747) for benchmarking and details of WhisperX. We also introduce more efficient batch inference resulting in large-v2 with *60-70x REAL TIME speed.* Repo will be updated soon with this efficient batch inference.
- Batch processing: Add `--vad_filter --parallel_bs [int]` for transcribing long audio file in batches (only supported with VAD filtering). Replace `[int]` with a batch size that fits your GPU memory, e.g. `--parallel_bs 16`.
- VAD filtering: Voice Activity Detection (VAD) from [Pyannote.audio](https://huggingface.co/pyannote/voice-activity-detection) is used as a preprocessing step to remove reliance on whisper timestamps and only transcribe audio segments containing speech. add `--vad_filter` flag, increases timestamp accuracy and robustness (requires more GPU mem due to 30s inputs in wav2vec2)
- Character level timestamps (see `*.char.ass` file output)
To **enable VAD filtering and Diarization**, include your Hugging Face access token that you can generate from [Here](https://huggingface.co/settings/tokens) after the `--hf_token` argument and accept the user agreement for the following models: [Segmentation](https://huggingface.co/pyannote/segmentation) , [Voice Activity Detection (VAD)](https://huggingface.co/pyannote/voice-activity-detection) , and [Speaker Diarization](https://huggingface.co/pyannote/speaker-diarization)
The phoneme ASR alignment model is *language-specific*, for tested languages these models are [automatically picked from torchaudio pipelines or huggingface](https://github.com/m-bain/whisperX/blob/e909f2f766b23b2000f2d95df41f9b844ac53e49/whisperx/transcribe.py#L22).
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, uk, pt}`. If the detected language is not in this list, you need to find a phoneme-based ASR model from [huggingface model hub](https://huggingface.co/models) and test it 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.
- If not using VAD filter, whisperx 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)
- Overlapping speech is not handled particularly well by whisper nor whisperx
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.
<ahref="https://www.buymeacoffee.com/maxhbain"target="_blank"><imgsrc="https://cdn.buymeacoffee.com/buttons/default-orange.png"alt="Buy Me A Coffee"height="41"width="174"></a>
This work, and my PhD, is supported by the [VGG (Visual Geometry Group)](https://www.robots.ox.ac.uk/~vgg/) and University of Oxford.
Of course, this is builds on [openAI's whisper](https://github.com/openai/whisper).
And borrows important alignment code from [PyTorch tutorial on forced alignment](https://pytorch.org/tutorials/intermediate/forced_alignment_with_torchaudio_tutorial.html)
