config.json

{
  "architectures": [
    "ASRModel"
  ],
  "attn_implementation": "flash_attention_2",
  "audio_config": {
    "_name_or_path": "openai/whisper-large-v3-turbo",
    "activation_dropout": 0.0,
    "activation_function": "gelu",
    "apply_spec_augment": false,
    "architectures": [
      "WhisperForConditionalGeneration"
    ],
    "attention_dropout": 0.0,
    "bos_token_id": 50257,
    "classifier_proj_size": 256,
    "d_model": 1280,
    "decoder_attention_heads": 20,
    "decoder_ffn_dim": 5120,
    "decoder_layerdrop": 0.0,
    "decoder_layers": 4,
    "decoder_start_token_id": 50258,
    "dropout": 0.0,
    "dtype": "bfloat16",
    "encoder_attention_heads": 20,
    "encoder_ffn_dim": 5120,
    "encoder_layerdrop": 0.0,
    "encoder_layers": 32,
    "eos_token_id": 50257,
    "init_std": 0.02,
    "mask_feature_length": 10,
    "mask_feature_min_masks": 0,
    "mask_feature_prob": 0.0,
    "mask_time_length": 10,
    "mask_time_min_masks": 2,
    "mask_time_prob": 0.05,
    "max_source_positions": 1500,
    "max_target_positions": 448,
    "median_filter_width": 7,
    "model_type": "whisper",
    "num_hidden_layers": 32,
    "num_mel_bins": 128,
    "pad_token_id": 50257,
    "scale_embedding": false,
    "use_cache": true,
    "use_weighted_layer_sum": false,
    "vocab_size": 51866
  },
  "audio_model_id": "openai/whisper-large-v3-turbo",
  "audio_sample_rate": 16000,
  "auto_map": {
    "AutoConfig": "asr_config.ASRConfig",
    "AutoModel": "asr_modeling.ASRModel",
    "AutoModelForSpeechSeq2Seq": "asr_modeling.ASRModel",
    "AutoProcessor": "asr_processing.ASRProcessor"
  },
  "custom_pipelines": {
    "automatic-speech-recognition": {
      "impl": "asr_pipeline.ASRPipeline",
      "pt": [
        "AutoModelForSpeechSeq2Seq"
      ],
      "tf": [],
      "type": "audio"
    }
  },
  "downsample_rate": 5,
  "dtype": "bfloat16",
  "encoder_dim": 1280,
  "inference_diversity_penalty": 0.0,
  "inference_warmup_tokens": 10,
  "label_smoothing": 0.0,
  "llm_dim": 2048,
  "max_new_tokens": 96,
  "min_new_tokens": 0,
  "model_dtype": "bfloat16",
  "model_type": "asr_model",
  "num_experts": 4,
  "num_experts_per_tok": 2,
  "pipeline_tag": "automatic-speech-recognition",
  "projector_dropout": 0.0,
  "projector_hidden_dim": null,
  "projector_init_std": 0.02,
  "projector_input_noise": 0.0,
  "projector_num_layers": 2,
  "projector_pool_stride": 4,
  "projector_type": "moe",
  "qformer_hidden_size": null,
  "qformer_intermediate_size": null,
  "qformer_num_heads": 16,
  "qformer_num_layers": 2,
  "qformer_window_size": 15,
  "router_aux_loss_coef": 0.01,
  "system_prompt": "/no_think /system_override",
  "text_config": {
    "_name_or_path": "HuggingFaceTB/SmolLM3-3B",
    "architectures": [
      "SmolLM3ForCausalLM"
    ],
    "attention_bias": false,
    "attention_dropout": 0.0,
    "bos_token_id": null,
    "dtype": "bfloat16",
    "eos_token_id": 128012,
    "hidden_act": "silu",
    "hidden_size": 2048,
    "initializer_range": 0.02,
    "intermediate_size": 11008,
    "layer_types": [
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention",
      "full_attention"
    ],
    "max_position_embeddings": 65536,
    "max_window_layers": 28,
    "mlp_bias": false,
    "model_type": "smollm3",
    "no_rope_layer_interval": 4,
    "no_rope_layers": [
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0,
      1,
      1,
      1,
      0
    ],
    "num_attention_heads": 16,
    "num_hidden_layers": 36,
    "num_key_value_heads": 4,
    "pretraining_tp": 2,
    "rms_norm_eps": 1e-06,
    "rope_scaling": null,
    "rope_theta": 5000000.0,
    "sliding_window": null,
    "use_cache": false,
    "use_sliding_window": false,
    "vocab_size": 128257
  },
  "text_model_id": "HuggingFaceTB/SmolLM3-3B",
  "transformers_version": "4.57.3",
  "use_cache": false,
  "use_specaugment": true,
  "user_prompt": "Transcribe: <audio>",
  "vocab_size": 128257
}