{ "acoustic_tokenizer_config": { "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "model_type": "vibevoice_acoustic_tokenizer", "channels": 1, "corpus_normalize": 0.0, "causal": true, "vae_dim": 64, "fix_std": 0.5, "std_dist_type": "gaussian", "conv_norm": "none", "pad_mode": "constant", "layernorm_eps": 1e-05, "disable_last_norm": true, "layernorm": "RMSNorm", "layernorm_elementwise_affine": true, "conv_bias": true, "layer_scale_init_value": 1e-06, "weight_init_value": 0.01, "mixer_layer": "depthwise_conv", "encoder_n_filters": 32, "encoder_ratios": [ 8, 5, 5, 4, 2, 2 ], "encoder_depths": "3-3-3-3-3-3-8", "decoder_ratios": [ 8, 5, 5, 4, 2, 2 ], "decoder_n_filters": 32, "decoder_depths": null }, "semantic_tokenizer_config": { "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "model_type": "vibevoice_semantic_tokenizer", "channels": 1, "corpus_normalize": 0.0, "causal": true, "vae_dim": 128, "fix_std": 0, "std_dist_type": "none", "conv_norm": "none", "pad_mode": "constant", "layernorm_eps": 1e-05, "disable_last_norm": true, "layernorm": "RMSNorm", "layernorm_elementwise_affine": true, "conv_bias": true, "layer_scale_init_value": 1e-06, "weight_init_value": 0.01, "mixer_layer": "depthwise_conv", "encoder_n_filters": 32, "encoder_ratios": [ 8, 5, 5, 4, 2, 2 ], "encoder_depths": "3-3-3-3-3-3-8" }, "decoder_config": { "attention_bias": false, "attention_dropout": 0.0, "attn_output_gate": true, "dtype": "bfloat16", "eos_token_id": 248044, "full_attention_interval": 4, "head_dim": 256, "hidden_act": "silu", "hidden_size": 2560, "initializer_range": 0.02, "intermediate_size": 9216, "layer_types": [ "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention", "linear_attention", "linear_attention", "linear_attention", "full_attention" ], "linear_conv_kernel_dim": 4, "linear_key_head_dim": 128, "linear_num_key_heads": 16, "linear_num_value_heads": 32, "linear_value_head_dim": 128, "max_position_embeddings": 262144, "mlp_only_layers": [], "model_type": "qwen3_5_text", "mtp_num_hidden_layers": 1, "mtp_use_dedicated_embeddings": false, "num_attention_heads": 16, "num_hidden_layers": 32, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "tie_word_embeddings": true, "use_cache": true, "vocab_size": 248320, "mamba_ssm_dtype": "float32", "rope_parameters": { "mrope_interleaved": true, "mrope_section": [ 11, 11, 10 ], "rope_type": "default", "rope_theta": 10000000, "partial_rotary_factor": 0.25 } }, "diffusion_head_config": { "hidden_size": 2560, "head_layers": 4, "head_ffn_ratio": 3.0, "rms_norm_eps": 1e-05, "latent_size": 64, "speech_vae_dim": 64, "prediction_type": "v_prediction", "diffusion_type": "ddpm", "ddpm_num_steps": 1000, "ddpm_num_inference_steps": 20, "ddpm_beta_schedule": "cosine", "ddpm_batch_mul": 4, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": null, "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "", "_attn_implementation_autoset": false, "model_type": "vibevoice_diffusion_head" }, "acoustic_vae_dim": 64, "semantic_vae_dim": 128, "return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": "bfloat16", "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "chunk_size_feed_forward": 0, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": [ "VibeVoiceForConditionalGeneration" ], "finetuning_task": null, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "tokenizer_class": null, "prefix": null, "bos_token_id": null, "pad_token_id": null, "eos_token_id": null, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "microsoft/VibeVoice-1.5B", "_attn_implementation_autoset": true, "transformers_version": "4.51.3", "model_type": "vibevoice" }