Instructions to use 2Noise/ChatTTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ChatTTS
How to use 2Noise/ChatTTS with ChatTTS:
import ChatTTS import torchaudio chat = ChatTTS.Chat() chat.load_models(compile=False) # Set to True for better performance texts = ["PUT YOUR TEXT HERE",] wavs = chat.infer(texts, ) torchaudio.save("output1.wav", torch.from_numpy(wavs[0]), 24000) - Notebooks
- Google Colab
- Kaggle
Chat.load_models() got an unexpected keyword argument 'compile'
#18
by SIddz - opened
Help me solve this someone!
Download the ChatTTS models locally and specify your local model address in Chat.load_models().
eg:
chat.load_models(source='local',local_path='model')
#chat.load_models(compile=False) # Set to True for better performance
chat.load(source="local", force_redownload=False, compile=False, custom_path=r'D:\downloads\ChatTTS')
I checked the core.py, and by using this, not sure it will work on my PC or not.