search

collabora / WhisperSpeech

An Open Source text-to-speech system built by inverting Whisper.
https://collabora.github.io/WhisperSpeech/
MIT License
3.54k stars 185 forks source link

In "2A. Whisper quantization dataset preparation.ipynb:,where is "vad.flac_to_vad_name" #138

Open ScottishFold007 opened 1 month ago

ScottishFold007 commented 1 month ago

In "2A. Whisper quantization dataset preparation.ipynb:,where is "vad.flac_to_vad_name":

# load some VAD ouputs
ds = wds.WebDataset(
    vad.flac_to_vad_name(flac_url)
).decode().to_tuple('vad.npy')
chunks = [x[0] for x in progress_bar(ds, total='noinfer')]