| { | |
| "model_type": "chatterbox", | |
| "version": "multilingual-1.0", | |
| "t3_config": { | |
| "text_tokens_dict_size": 2454, | |
| "speech_tokens_dict_size": 8194, | |
| "start_text_token": 255, | |
| "stop_text_token": 0, | |
| "max_text_tokens": 2048, | |
| "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 | |
| }, | |
| "quantization": { | |
| "bits": 4, | |
| "group_size": 64, | |
| "quantized_components": [ | |
| "t3.tfmr.model.layers" | |
| ] | |
| } | |
| } |