Text-to-Speech
MLX
Safetensors
Chinese
English
dense
tts
apple-silicon
voice-cloning
ming
custom_code
Instructions to use cs2764/Ming-omni-tts-0.5B-8bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use cs2764/Ming-omni-tts-0.5B-8bit-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Ming-omni-tts-0.5B-8bit-mlx cs2764/Ming-omni-tts-0.5B-8bit-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "aggregator_config": { | |
| "attn_mask_enabled": false, | |
| "depth": 8, | |
| "dropout": 0.0, | |
| "hidden_size": 1024, | |
| "mlp_ratio": 4, | |
| "num_heads": 16 | |
| }, | |
| "architectures": [ | |
| "BailingMMNativeForConditionalGeneration" | |
| ], | |
| "audio_tokenizer_config": { | |
| "_name_or_path": "", | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "AudioVAE" | |
| ], | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": null, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "dec_kwargs": { | |
| "backbone": { | |
| "_attn_implementation": "flash_attention_2", | |
| "attention_dropout": 0.0, | |
| "attn_implementation": null, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "is_causal": true, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 0, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 14, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 64, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.1", | |
| "use_cache": false, | |
| "use_sliding_window": true, | |
| "vocab_size": 1 | |
| }, | |
| "latent_dim": 64, | |
| "output_dim": 882 | |
| }, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "early_stopping": false, | |
| "enc_kwargs": { | |
| "backbone": { | |
| "_attn_implementation": "flash_attention_2", | |
| "attention_dropout": 0.0, | |
| "attn_implementation": null, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "is_causal": true, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 0, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 14, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 64, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.1", | |
| "use_cache": false, | |
| "use_sliding_window": true, | |
| "vocab_size": 1 | |
| }, | |
| "hop_size": 882, | |
| "input_dim": 882, | |
| "latent_dim": 64 | |
| }, | |
| "init_method": "kaiming", | |
| "patch_size": 4, | |
| "sample_rate": 44100, | |
| "semantic_module_kwargs": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "use_bfloat16": false | |
| }, | |
| "auto_map": { | |
| "AutoConfig": "configuration_bailingmm.BailingMMConfig" | |
| }, | |
| "ditar_config": { | |
| "attn_backend": "torch", | |
| "attn_mask_enabled": false, | |
| "depth": 8, | |
| "dropout": 0.0, | |
| "hidden_size": 1024, | |
| "history_patch_size": 32, | |
| "mlp_ratio": 4, | |
| "num_heads": 16, | |
| "patch_size": 4 | |
| }, | |
| "llm_config": { | |
| "_name_or_path": "", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attn_implementation": null, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "hidden_act": "silu", | |
| "hidden_size": 896, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 4864, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 21, | |
| "model_type": "qwen2", | |
| "num_attention_heads": 14, | |
| "num_hidden_layers": 24, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 1e-06, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": 32768, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.43.1", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| }, | |
| "mlp_depth": 2, | |
| "model_type": "dense", | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.52.4" | |
| } |