Closed ebolam closed 11 months ago
Also added in fixes for tortoise TTS which in theory speeds up generation by x15.
Requires users running the following to install tortoise and dependencies without messing up transformers:
pip install git+https://github.com/neonbjb/tortoise-tts OmegaConf deepspeed
pip install torchaudio --index-url https://download.pytorch.org/whl/cu118
pip install -r requirements.txt --no-dependencies
Need experimental features turned on in the UI and turn on generate audio. Should background process the text into ogg files for playback in the UI (was there before, just faster now with better chunking)
We should not override the PAD id at all times just to get rid of a message, I agree with the idea of suppressing the error by replicating what HF is doing, but we should only do so if the pad token is not present.
The code should use the tokenizer's pad id always. Is there another source of pad ids?
Minor change to remove the warning about "Setting
pad_token_id
toeos_token_id
:{eos_token_id} for open-end generation."