Instructions to use mikeyyyyyy/ChatTTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ChatTTS
How to use mikeyyyyyy/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
| num_audio_tokens: 626 | |
| num_text_tokens: 21178 | |
| gpt_config: | |
| hidden_size: 768 | |
| intermediate_size: 3072 | |
| num_attention_heads: 12 | |
| num_hidden_layers: 20 | |
| use_cache: False | |
| max_position_embeddings: 4096 | |
| # attn_implementation: flash_attention_2 | |
| spk_emb_dim: 192 | |
| spk_KL: False | |
| num_audio_tokens: 626 | |
| num_text_tokens: null | |
| num_vq: 4 | |