Instructions to use BricksDisplay/chatterbox-multilingual-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Chatterbox
How to use BricksDisplay/chatterbox-multilingual-ONNX with Chatterbox:
# pip install chatterbox-tts import torchaudio as ta from chatterbox.tts import ChatterboxTTS model = ChatterboxTTS.from_pretrained(device="cuda") text = "Ezreal and Jinx teamed up with Ahri, Yasuo, and Teemo to take down the enemy's Nexus in an epic late-game pentakill." wav = model.generate(text) ta.save("test-1.wav", wav, model.sr) # If you want to synthesize with a different voice, specify the audio prompt AUDIO_PROMPT_PATH="YOUR_FILE.wav" wav = model.generate(text, audio_prompt_path=AUDIO_PROMPT_PATH) ta.save("test-2.wav", wav, model.sr) - Notebooks
- Google Colab
- Kaggle
Create config.json
Browse files- config.json +43 -0
config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_type": "chatterbox",
|
| 3 |
+
"architectures": ["ChatterboxModel"],
|
| 4 |
+
"text_config": {
|
| 5 |
+
"architectures": ["LlamaForCausalLM"],
|
| 6 |
+
"attention_bias": false,
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 1,
|
| 9 |
+
"eos_token_id": [2, 6562],
|
| 10 |
+
"head_dim": 64,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 1024,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 4096,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 16,
|
| 19 |
+
"num_hidden_layers": 30,
|
| 20 |
+
"num_key_value_heads": 16,
|
| 21 |
+
"pretraining_tp": 1,
|
| 22 |
+
"rms_norm_eps": 1e-5,
|
| 23 |
+
"rope_scaling": {
|
| 24 |
+
"factor": 8.0,
|
| 25 |
+
"high_freq_factor": 4.0,
|
| 26 |
+
"low_freq_factor": 1.0,
|
| 27 |
+
"original_max_position_embeddings": 8192,
|
| 28 |
+
"rope_type": "llama3"
|
| 29 |
+
},
|
| 30 |
+
"rope_theta": 500000.0,
|
| 31 |
+
"tie_word_embeddings": false,
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 2454
|
| 35 |
+
},
|
| 36 |
+
"transformers.js_config": {
|
| 37 |
+
"use_external_data_format": true,
|
| 38 |
+
"kv_cache_dtype": {
|
| 39 |
+
"fp16": "float16",
|
| 40 |
+
"q4f16": "float16"
|
| 41 |
+
}
|
| 42 |
+
}
|
| 43 |
+
}
|