{ "_encoder_config_type": "whisper", "_llm_config_type": "qwen2", "adapter_downsample": 8, "architectures": [ "CovoAudioForCausalLM" ], "audio_token_index": 151671, "auto_map": { "AutoConfig": "configuration_covo_audio.CovoAudioConfig", "AutoModel": "modeling_covo_audio.CovoAudioForCausalLM" }, "dtype": "bfloat16", "encoder_config": { "_name_or_path": "openai/whisper-large-v3", "activation_dropout": 0.0, "activation_function": "gelu", "apply_spec_augment": false, "architectures": [ "WhisperForConditionalGeneration" ], "attention_dropout": 0.0, "begin_suppress_tokens": [ 220, 50257 ], "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": 32, "decoder_start_token_id": 50258, "dropout": 0.0, "dtype": "float16", "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_length": 448, "max_source_positions": 1500, "max_target_positions": 448, "median_filter_width": 7, "model_type": "whisper", "num_hidden_layers": 32, "num_mel_bins": 128, "scale_embedding": false, "use_cache": true, "use_weighted_layer_sum": false, "vocab_size": 51866 }, "llm_config": { "architectures": [ "Qwen2ForCausalLM" ], "attention_dropout": 0.0, "bos_token_id": 151643, "dtype": "bfloat16", "eos_token_id": 151643, "hidden_act": "silu", "hidden_size": 3584, "initializer_range": 0.02, "intermediate_size": 18944, "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" ], "max_position_embeddings": 131072, "max_window_layers": 28, "model_type": "qwen2", "num_attention_heads": 28, "num_hidden_layers": 28, "num_key_value_heads": 4, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "sliding_window": null, "use_cache": true, "use_mrope": false, "use_sliding_window": false, "vocab_size": 168055 }, "model_type": "covo_audio", "transformers_version": "4.57.1", "whisper_feats_dim": 1280 }