Fix issues for fairseq model handling and VC when speaker_wav is passed

coqui-ai / TTS

🐸💬 - a deep learning toolkit for Text-to-Speech, battle-tested in research and production

http://coqui.ai

Mozilla Public License 2.0

31.64k stars 3.78k forks source link

Fix issues for fairseq model handling and VC when speaker_wav is passed #3765

Open hanasim opened 1 month ago

hanasim commented 1 month ago

When we use the model "tts_models/eng/fairseq/vits", got the following error.

Error in text to speech: cannot access local variable 'dataset' where it is not associated with a value

at line ..../.conda/envs/venv/lib/python3.11/site-packages/TTS/utils/manage.py", line 304, in _set_model_item model_full_name = f"{model_type}--{lang}--{dataset}--{model}"

CLAassistant commented 1 month ago

All committers have signed the CLA.

eginhard commented 1 month ago

This repo is not maintained anymore. The issue is already fixed in our fork, available via pip install coqui-tts