Text-to-Speech
Transformers.js
ONNX
Chatterbox
speech
speech-generation
voice-cloning
multilingual-tts
quantized
q4
Instructions to use BricksDisplay/chatterbox-multilingual-ONNX-q4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers.js
How to use BricksDisplay/chatterbox-multilingual-ONNX-q4 with Transformers.js:
// npm i @huggingface/transformers import { pipeline } from '@huggingface/transformers'; // Allocate pipeline const pipe = await pipeline('text-to-speech', 'BricksDisplay/chatterbox-multilingual-ONNX-q4');
| { | |
| "model_type": "chatterbox", | |
| "architectures": [ | |
| "ChatterboxModel" | |
| ], | |
| "text_config": { | |
| "architectures": [ | |
| "LlamaForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 1, | |
| "eos_token_id": [ | |
| 2, | |
| 6562 | |
| ], | |
| "head_dim": 64, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4096, | |
| "max_position_embeddings": 131072, | |
| "mlp_bias": false, | |
| "model_type": "llama", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 30, | |
| "num_key_value_heads": 16, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": { | |
| "factor": 8.0, | |
| "high_freq_factor": 4.0, | |
| "low_freq_factor": 1.0, | |
| "original_max_position_embeddings": 8192, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000.0, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vocab_size": 2454 | |
| }, | |
| "transformers.js_config": { | |
| "use_external_data_format": false, | |
| "kv_cache_dtype": { | |
| "fp16": "float16", | |
| "q4f16": "float16" | |
| } | |
| } | |
| } |