## Summary
- Adds support for MP3, FLAC, OGG, and other audio formats when
uploading reference voices for cloning
- Replace WAV-only `audio_read()` with a `soundfile`-based
implementation
- Update web UI file picker to accept multiple audio formats
## Changes
- `pocket_tts/data/audio.py`: Use `soundfile` library instead of
Python's `wave` module
- `pocket_tts/main.py`: Preserve original file extension in temp files
for format detection
- `pocket_tts/main.py`: Add missing `truncate=True` to CLI generate
command
- `pocket_tts/static/index.html`: Update file input to accept
`.wav,.mp3,.flac,.ogg,.m4a,audio/*`
- `pyproject.toml`: Add `soundfile>=0.12.0` dependency
## Tested
- [x] Upload a WAV file as reference voice and generate speech
- [x] Upload an MP3 file as reference voice and generate speech
- [x] Upload a FLAC file as reference voice and generate speech
- [x] Verify CLI `--voice` option works with MP3 files
---------
Co-authored-by: Gabriel de Marmiesse <gabrieldemarmiesse@gmail.com>
Co-authored-by: Václav Volhejn <8401624+vvolhejn@users.noreply.github.com>
Without a specific commit, huggingface cannot be sure that the file has
not changed, so it needs to do a quick query to hf hub to check that
there were no new commits. This adds some latency to the CLI and
function calls, but it also prevents offline use, even if the files are
already present locally. This PRs fixes this. Now with the commit hash,
hf has the guarantee that the local files are the right ones and thus
doesn't need to query the hub every time.
Fix https://github.com/kyutai-labs/pocket-tts/pull/21
`torch.no_grad` is thread local, I now run the autoregressive generation
in a separate thread, in addition of the thread running mimi, and forgot
to add `torch.no_grad` to the function inside this thread.
