| { |
| "model_type": "fun_asr_nano", |
| "model_repo": "FunAudioLLM/Fun-ASR-Nano-2512", |
| "input_size": 560, |
| "qwen_tokenizer_path": "Qwen3-0.6B", |
| "frontend_conf": { |
| "fs": 16000, |
| "window": "hamming", |
| "n_mels": 80, |
| "frame_length": 25, |
| "frame_shift": 10, |
| "lfr_m": 7, |
| "lfr_n": 6, |
| "cmvn_file": null |
| }, |
| "audio_encoder_conf": { |
| "output_size": 512, |
| "attention_heads": 4, |
| "linear_units": 2048, |
| "num_blocks": 50, |
| "tp_blocks": 20, |
| "dropout_rate": 0.1, |
| "positional_dropout_rate": 0.1, |
| "attention_dropout_rate": 0.1, |
| "normalize_before": true, |
| "kernel_size": 11, |
| "sanm_shift": 0, |
| "feat_permute": true |
| }, |
| "audio_adaptor_conf": { |
| "downsample_rate": 1, |
| "use_low_frame_rate": true, |
| "ffn_dim": 2048, |
| "llm_dim": 1024, |
| "encoder_dim": 512, |
| "n_layer": 2, |
| "attention_heads": 8 |
| }, |
| "text_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": 1024, |
| "initializer_range": 0.02, |
| "intermediate_size": 3072, |
| "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": 1e-06, |
| "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 |
| }, |
| "default_max_tokens": 512 |
| } |
|
|
