TRY-ER
commented
1 month ago Raise the issue at https://github.com/coqui-ai/TTS.git for better support. This repo specifically forked to handle indic language deployment and it's behind several commits from the source repo. Better use the source repo and raise the issue there to resolve.
sudo apt-get install libsndfile1-dev ffmpeg enchant conda create -n tts-env conda activate tts-env pip3 install -U torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu113 git clone https://github.com/gokulkarthik/Trainer cd Trainer pip3 install -e .[all] cd .. git clone https://github.com/gokulkarthik/TTS
cd TTS pip3 install -e .[all] cd ..
I have followed all these steps and added TTS folder to my project. i want to use other language models to convert text to speech.
how can use these models.
i hav tried using
model_path = "/Users/prok/models/v1/as/fastpitch/best_model.pth" config_path = "/Users/prok/models/v1/as/fastpitch/config.json" vocoder_path = "/Users/prok/models/v1/as/hifigan/best_model.pth" vocoder_config_path = "/Users/prok/models/v1/as/hifigan/config.json" tts = TTS(model_path=model_path, config_path=config_path, vocoder_path=vocoder_path, vocoder_config_path=vocoder_config_path).to(device_id)
but gets an error that speaker id is not valids when i use TTS from https://github.com/coqui-ai/TTS.git
secondly, when I use git clone https://github.com/gokulkarthik/TTS I get an error that ModuleNotFoundError("No module named 'TTS.api'") for line: from TTS.TTS.api import TTS