| license: apache-2.0 | |
| pipeline_tag: text-to-speech | |
| tags: | |
| - text-to-speech | |
| - speech | |
| - speech-generation | |
| - voice-cloning | |
| - mlx | |
| - tts | |
| # Chatterbox Multilingual (MLX) - INT8 | |
| Multilingual Chatterbox TTS weights in MLX format (int8). | |
| ## Files | |
| - `model.safetensors` (0.90 GB) | |
| - `config.json` | |
| - `grapheme_mtl_merged_expanded_v1.json` | |
| - `Cangjie5_TC.json` | |
| ## Usage (Swift) | |
| ``` | |
| generate \ | |
| --weights-dir /path/to/weights \ | |
| --text "Hello world." \ | |
| --lang en \ | |
| --ref-wav-path /path/to/reference.wav \ | |
| --out-wav /path/to/output.wav | |
| ``` | |
| ## Usage (Python MLX) | |
| ```python | |
| from chatterbox.model import Model | |
| model = Model.from_pretrained("/path/to/weights") | |
| ``` | |
| Notes: | |
| - S3TokenizerV2 weights are loaded from the HF cache (`mlx-community/S3TokenizerV2`) unless included. | |