Instructions to use mlx-community/chatterbox-multilingual-v3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/chatterbox-multilingual-v3 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir chatterbox-multilingual-v3 mlx-community/chatterbox-multilingual-v3
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "model_type": "chatterbox", | |
| "version": "1.0", | |
| "t3_model": "v3", | |
| "multilingual": true, | |
| "vocab_size": 2454, | |
| "text_preprocessing": "NFKD,fullcase", | |
| "t3_config": { | |
| "text_tokens_dict_size": 2454, | |
| "start_text_token": 255, | |
| "stop_text_token": 0, | |
| "max_text_tokens": 2048, | |
| "speech_tokens_dict_size": 8194, | |
| "start_speech_token": 6561, | |
| "stop_speech_token": 6562, | |
| "max_speech_tokens": 4096, | |
| "llama_config_name": "Llama_520M", | |
| "input_pos_emb": "learned", | |
| "speech_cond_prompt_len": 150, | |
| "encoder_type": "voice_encoder", | |
| "speaker_embed_size": 256, | |
| "use_perceiver_resampler": true, | |
| "emotion_adv": true | |
| } | |
| } |