Text-to-Speech
Transformers
Safetensors
PyTorch
English
Chinese
breeze
text-generation
speech-generation
voice-clone
voice-design
voice-direction
cuda
Instructions to use BreezeBlue/Breeze-TTS-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use BreezeBlue/Breeze-TTS-2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="BreezeBlue/Breeze-TTS-2")# Load model directly from transformers import AutoModelForSeq2SeqLM model = AutoModelForSeq2SeqLM.from_pretrained("BreezeBlue/Breeze-TTS-2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "BreezeForConditionalGeneration" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "audio_embed_size": 2048, | |
| "audio_eos_token_id": 262145, | |
| "audio_num_codebooks": 16, | |
| "audio_token_id": 262144, | |
| "audio_vocab_size": 2051, | |
| "backbone_flavor": "llama-1B", | |
| "backbone_model_name_or_path": null, | |
| "backbone_model_type": "qwen3", | |
| "bos_token_id": 2, | |
| "codebook_eos_token_id": 0, | |
| "codebook_pad_token_id": 2050, | |
| "codec_config": { | |
| "_frame_rate": 12.5, | |
| "_name_or_path": "kyutai/mimi", | |
| "architectures": [ | |
| "MimiModel" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "audio_channels": 1, | |
| "codebook_dim": 256, | |
| "codebook_size": 2048, | |
| "compress": 2, | |
| "dilation_growth_rate": 2, | |
| "dtype": "bfloat16", | |
| "head_dim": 64, | |
| "hidden_act": "gelu", | |
| "hidden_size": 512, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 2048, | |
| "kernel_size": 7, | |
| "last_kernel_size": 3, | |
| "layer_scale_initial_scale": 0.01, | |
| "max_position_embeddings": 8000, | |
| "model_type": "mimi", | |
| "norm_eps": 0.00001, | |
| "normalize": false, | |
| "num_attention_heads": 8, | |
| "num_filters": 64, | |
| "num_hidden_layers": 8, | |
| "num_key_value_heads": 8, | |
| "num_quantizers": 32, | |
| "num_residual_layers": 1, | |
| "num_semantic_quantizers": 1, | |
| "pad_mode": "constant", | |
| "residual_kernel_size": 3, | |
| "rope_theta": 10000.0, | |
| "sampling_rate": 24000, | |
| "sliding_window": 250, | |
| "trim_right_ratio": 1.0, | |
| "upsample_groups": 512, | |
| "upsampling_ratios": [ | |
| 8, | |
| 6, | |
| 5, | |
| 4 | |
| ], | |
| "use_cache": false, | |
| "use_causal_conv": true, | |
| "use_conv_shortcut": false, | |
| "use_streaming": false, | |
| "vector_quantization_hidden_dimension": 256 | |
| }, | |
| "decoder_flavor": "llama-100M", | |
| "depth_decoder_config": { | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "audio_embed_size": 2048, | |
| "backbone_hidden_size": 2048, | |
| "codebook_loss_weights": [ | |
| 3 | |
| ], | |
| "dtype": "bfloat16", | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 1024, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 8192, | |
| "max_position_embeddings": 33, | |
| "mlp_bias": false, | |
| "model_type": "breeze_depth_decoder_model", | |
| "num_attention_heads": 8, | |
| "num_codebooks": 16, | |
| "num_hidden_layers": 12, | |
| "num_key_value_heads": 2, | |
| "rms_norm_eps": 0.00001, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 0.0078125, | |
| "low_freq_factor": 0.001953125, | |
| "original_max_position_embeddings": 16, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000, | |
| "use_cache": true, | |
| "vocab_size": 2051 | |
| }, | |
| "depth_header_loss_weight": 1.0, | |
| "dtype": "bfloat16", | |
| "eos_token_id": 1, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 2048, | |
| "mlp_bias": false, | |
| "model_type": "breeze", | |
| "num_attention_heads": 16, | |
| "num_codebooks": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "pad_token_id": 0, | |
| "rms_norm_eps": 0.00001, | |
| "rope_scaling": { | |
| "factor": 32.0, | |
| "high_freq_factor": 0.5, | |
| "low_freq_factor": 0.125, | |
| "original_max_position_embeddings": 1024, | |
| "rope_type": "llama3" | |
| }, | |
| "rope_theta": 500000, | |
| "text_encoder_bucket_max_length_ratio": 4.0, | |
| "text_encoder_config": { | |
| "add_cross_attention": false, | |
| "architectures": [ | |
| "T5Gemma2TextEncoder" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "attn_logit_softcapping": null, | |
| "bad_words_ids": null, | |
| "begin_suppress_tokens": null, | |
| "bos_token_id": 2, | |
| "chunk_size_feed_forward": 0, | |
| "cross_attention_hidden_size": null, | |
| "decoder_start_token_id": null, | |
| "diversity_penalty": 0.0, | |
| "do_sample": false, | |
| "dropout_rate": 0.0, | |
| "dtype": "bfloat16", | |
| "early_stopping": false, | |
| "encoder_no_repeat_ngram_size": 0, | |
| "eoi_token_index": 256000, | |
| "eos_token_id": 1, | |
| "exponential_decay_length_penalty": null, | |
| "final_logit_softcapping": null, | |
| "finetuning_task": null, | |
| "forced_bos_token_id": null, | |
| "forced_eos_token_id": null, | |
| "head_dim": 256, | |
| "hidden_activation": "gelu_pytorch_tanh", | |
| "hidden_size": 1152, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6912, | |
| "is_decoder": false, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1 | |
| }, | |
| "layer_types": [ | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "sliding_attention", | |
| "full_attention", | |
| "sliding_attention", | |
| "sliding_attention" | |
| ], | |
| "length_penalty": 1.0, | |
| "max_length": 20, | |
| "max_position_embeddings": 32768, | |
| "min_length": 0, | |
| "model_type": "t5gemma2_text", | |
| "no_repeat_ngram_size": 0, | |
| "num_attention_heads": 4, | |
| "num_beam_groups": 1, | |
| "num_beams": 1, | |
| "num_hidden_layers": 26, | |
| "num_key_value_heads": 1, | |
| "num_return_sequences": 1, | |
| "output_attentions": false, | |
| "output_hidden_states": false, | |
| "output_scores": false, | |
| "pad_token_id": 0, | |
| "preferred_attn_implementation": "flash_attention_2", | |
| "prefix": null, | |
| "problem_type": null, | |
| "pruned_heads": {}, | |
| "query_pre_attn_scalar": 256, | |
| "remove_invalid_values": false, | |
| "repetition_penalty": 1.0, | |
| "requires_grad": false, | |
| "return_dict": true, | |
| "return_dict_in_generate": false, | |
| "rms_norm_eps": 0.000001, | |
| "rope_parameters": { | |
| "full_attention": { | |
| "factor": 8.0, | |
| "rope_theta": 1000000, | |
| "rope_type": "linear" | |
| }, | |
| "sliding_attention": { | |
| "rope_theta": 10000, | |
| "rope_type": "default" | |
| } | |
| }, | |
| "sep_token_id": null, | |
| "sliding_window": 512, | |
| "suppress_tokens": null, | |
| "task_specific_params": null, | |
| "temperature": 1.0, | |
| "tf_legacy_loss": false, | |
| "tie_encoder_decoder": false, | |
| "tie_word_embeddings": true, | |
| "tokenizer_class": null, | |
| "top_k": 50, | |
| "top_p": 1.0, | |
| "torchscript": false, | |
| "typical_p": 1.0, | |
| "use_bfloat16": false, | |
| "use_bidirectional_attention": false, | |
| "use_cache": true, | |
| "vocab_size": 262158 | |
| }, | |
| "text_encoder_lora_config": { | |
| "alpha": 16.0, | |
| "dropout": 0.05, | |
| "enabled": false, | |
| "freeze_base_model": true, | |
| "layers": [ | |
| 0, | |
| 1, | |
| 2, | |
| 3, | |
| 4, | |
| 5, | |
| 6, | |
| 7, | |
| 8, | |
| 9, | |
| 10, | |
| 11, | |
| 12, | |
| 13, | |
| 14, | |
| 15, | |
| 16, | |
| 17, | |
| 18, | |
| 19, | |
| 20, | |
| 21, | |
| 22, | |
| 23, | |
| 24, | |
| 25 | |
| ], | |
| "merged_into_base": true, | |
| "rank": 8, | |
| "target_modules": [ | |
| "q_proj", | |
| "v_proj", | |
| "o_proj" | |
| ] | |
| }, | |
| "text_encoder_proj_type": "linear", | |
| "text_encoder_special_tokens_config": { | |
| "enabled": false, | |
| "freeze_base_embeddings": true, | |
| "initializer_token_ids": { | |
| "<ins_bos>": [ | |
| 236820, | |
| 22768, | |
| 236813 | |
| ], | |
| "<ins_eos>": [ | |
| 954, | |
| 22768, | |
| 236813 | |
| ], | |
| "[S0]": [ | |
| 262146 | |
| ], | |
| "[S1]": [ | |
| 262147 | |
| ], | |
| "[S2]": [ | |
| 262148 | |
| ], | |
| "[S3]": [ | |
| 262149 | |
| ], | |
| "[S4]": [ | |
| 262150 | |
| ], | |
| "[S5]": [ | |
| 262151 | |
| ], | |
| "[S6]": [ | |
| 262152 | |
| ], | |
| "[S7]": [ | |
| 262153 | |
| ], | |
| "[S8]": [ | |
| 262154 | |
| ], | |
| "[S9]": [ | |
| 262155 | |
| ] | |
| }, | |
| "initializers": { | |
| "<ins_bos>": "<instruction>", | |
| "<ins_eos>": "</instruction>", | |
| "[S0]": "[S0]", | |
| "[S1]": "[S1]", | |
| "[S2]": "[S2]", | |
| "[S3]": "[S3]", | |
| "[S4]": "[S4]", | |
| "[S5]": "[S5]", | |
| "[S6]": "[S6]", | |
| "[S7]": "[S7]", | |
| "[S8]": "[S8]", | |
| "[S9]": "[S9]" | |
| }, | |
| "instruction_tokens": { | |
| "bos": "<ins_bos>", | |
| "eos": "<ins_eos>" | |
| }, | |
| "merged_into_base": true, | |
| "num_added_tokens": 12, | |
| "speaker_tokens": [ | |
| "[S0]", | |
| "[S1]", | |
| "[S2]", | |
| "[S3]", | |
| "[S4]", | |
| "[S5]", | |
| "[S6]", | |
| "[S7]", | |
| "[S8]", | |
| "[S9]" | |
| ], | |
| "token_ids": { | |
| "<ins_bos>": 262156, | |
| "<ins_eos>": 262157, | |
| "[S0]": 262146, | |
| "[S1]": 262147, | |
| "[S2]": 262148, | |
| "[S3]": 262149, | |
| "[S4]": 262150, | |
| "[S5]": 262151, | |
| "[S6]": 262152, | |
| "[S7]": 262153, | |
| "[S8]": 262154, | |
| "[S9]": 262155 | |
| }, | |
| "tokens": [ | |
| "[S0]", | |
| "[S1]", | |
| "[S2]", | |
| "[S3]", | |
| "[S4]", | |
| "[S5]", | |
| "[S6]", | |
| "[S7]", | |
| "[S8]", | |
| "[S9]", | |
| "<ins_bos>", | |
| "<ins_eos>" | |
| ], | |
| "trainable": true | |
| }, | |
| "text_vocab_size": 262158, | |
| "tie_codebooks_embeddings": true, | |
| "tie_word_embeddings": false, | |
| "transformers_version": "4.57.3", | |
| "use_cache": true, | |
| "vocab_size": 2051, | |
| "backbone_config": { | |
| "architectures": [ | |
| "Qwen3ForCausalLM" | |
| ], | |
| "attention_bias": false, | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151645, | |
| "head_dim": 128, | |
| "hidden_act": "silu", | |
| "hidden_size": 2048, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 6144, | |
| "max_position_embeddings": 40960, | |
| "max_window_layers": 28, | |
| "model_type": "qwen3", | |
| "num_attention_heads": 16, | |
| "num_hidden_layers": 28, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 0.000001, | |
| "rope_scaling": null, | |
| "rope_theta": 1000000, | |
| "sliding_window": null, | |
| "tie_word_embeddings": true, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.51.0", | |
| "use_cache": true, | |
| "use_sliding_window": false, | |
| "vocab_size": 151936 | |
| } | |
| } | |