| { |
| "architectures": [ |
| "Qwen3ASRForConditionalGeneration" |
| ], |
| "audio_config": { |
| "activation_dropout": 0.0, |
| "activation_function": "gelu", |
| "attention_dropout": 0.0, |
| "d_model": 32, |
| "downsample_hidden_size": 16, |
| "dropout": 0.0, |
| "encoder_attention_heads": 4, |
| "encoder_ffn_dim": 64, |
| "encoder_layers": 2, |
| "initializer_range": 0.02, |
| "max_position_embeddings": 13, |
| "model_type": "qwen3_asr_encoder", |
| "n_window": 50, |
| "n_window_infer": 800, |
| "num_mel_bins": 128, |
| "output_dim": 64, |
| "scale_embedding": false |
| }, |
| "audio_token_id": 151676, |
| "dtype": "float32", |
| "eos_token_id": [ |
| 151643, |
| 151645 |
| ], |
| "initializer_range": 0.02, |
| "model_type": "qwen3_asr", |
| "pad_token_id": 151645, |
| "text_config": { |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": null, |
| "eos_token_id": null, |
| "head_dim": 16, |
| "hidden_act": "silu", |
| "hidden_size": 64, |
| "initializer_range": 0.02, |
| "intermediate_size": 128, |
| "layer_types": [ |
| "full_attention", |
| "full_attention" |
| ], |
| "max_position_embeddings": 65536, |
| "max_window_layers": 28, |
| "model_type": "qwen3", |
| "num_attention_heads": 4, |
| "num_hidden_layers": 2, |
| "num_key_value_heads": 2, |
| "pad_token_id": null, |
| "rms_norm_eps": 1e-06, |
| "rope_parameters": { |
| "rope_theta": 1000000.0, |
| "rope_type": "default" |
| }, |
| "sliding_window": null, |
| "tie_word_embeddings": true, |
| "use_cache": true, |
| "use_sliding_window": false, |
| "vocab_size": 151936 |
| }, |
| "tie_word_embeddings": true, |
| "timestamp_token_id": 151705, |
| "token_classification_bias": false, |
| "transformers_version": "5.13.0.dev0" |
| } |
|
|