{ "adapter_inner_dim": 512, "architectures": [ "OmniSpeechModel" ], "audio_encoder_config": { "_attn_implementation_autoset": true, "activation_dropout": 0.0, "activation_function": "gelu", "attention_dropout": 0.0, "d_model": 1280, "dropout": 0.0, "encoder_attention_heads": 20, "encoder_ffn_dim": 5120, "encoder_layerdrop": 0.0, "encoder_layers": 32, "init_std": 0.02, "max_source_positions": 1500, "model_type": "qwen2_audio_encoder", "num_hidden_layers": 32, "num_mel_bins": 128, "scale_embedding": false }, "conv_kernel_sizes": "5,5", "interleave_strategy": "4:8", "llm_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": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "max_position_embeddings": 40960, "max_window_layers": 36, "model_type": "qwen3", "num_attention_heads": 32, "num_hidden_layers": 36, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 151673 }, "lora_config": null, "torch_dtype": "bfloat16", "transformers_version": "4.51.0", "tts_lm_config": { "_attn_implementation_autoset": true, "architectures": [ "Qwen3ForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "eos_token_id": 151643, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 6144, "max_position_embeddings": 32768, "max_window_layers": 28, "model_type": "qwen3", "num_attention_heads": 16, "num_hidden_layers": 28, "num_key_value_heads": 8, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000, "sliding_window": null, "tie_word_embeddings": true, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 168055 } }