|
{ |
|
"architectures": [ |
|
"TasteForConditionalGeneration" |
|
], |
|
"asr_config": { |
|
"_attn_implementation_autoset": false, |
|
"_name_or_path": "openai/whisper-large-v3", |
|
"activation_dropout": 0.0, |
|
"activation_function": "gelu", |
|
"add_cross_attention": false, |
|
"apply_spec_augment": false, |
|
"architectures": [ |
|
"WhisperForConditionalGeneration" |
|
], |
|
"attention_dropout": 0.0, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": [ |
|
220, |
|
50257 |
|
], |
|
"bos_token_id": 50257, |
|
"chunk_size_feed_forward": 0, |
|
"classifier_proj_size": 256, |
|
"cross_attention_hidden_size": null, |
|
"d_model": 1280, |
|
"decoder_attention_heads": 20, |
|
"decoder_ffn_dim": 5120, |
|
"decoder_layerdrop": 0.0, |
|
"decoder_layers": 32, |
|
"decoder_start_token_id": 50258, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"dropout": 0.0, |
|
"early_stopping": false, |
|
"encoder_attention_heads": 20, |
|
"encoder_ffn_dim": 5120, |
|
"encoder_layerdrop": 0.0, |
|
"encoder_layers": 32, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": 50257, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"init_std": 0.02, |
|
"is_decoder": false, |
|
"is_encoder_decoder": true, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_penalty": 1.0, |
|
"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, |
|
"min_length": 0, |
|
"model_type": "whisper", |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_hidden_layers": 32, |
|
"num_mel_bins": 128, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": 50256, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"scale_embedding": false, |
|
"sep_token_id": null, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": true, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": "float16", |
|
"torchscript": false, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"use_cache": true, |
|
"use_weighted_layer_sum": false, |
|
"vocab_size": 51866 |
|
}, |
|
"audio_tower_config": { |
|
"_attn_implementation_autoset": false, |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"architectures": null, |
|
"audio_dropout_ratio": 0.0, |
|
"audio_embed_dim": 1280, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder__target_hidden_layer": 6, |
|
"encoder__unfreeze_hidden_layers_from_last": 1, |
|
"encoder_input_size": null, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"is_joint_encoder_segmenter": true, |
|
"kwargs_for_joint_encoder_segmenter": { |
|
"dtype": "bfloat16", |
|
"forward_type": "asr_attn_pooling", |
|
"is_word_level": true, |
|
"make_v_proj_identity": true, |
|
"model_name_or_path": "distil-whisper/distil-large-v3", |
|
"skip_prefix_idx": 4, |
|
"use_custom": true |
|
}, |
|
"kwargs_for_quantizer": { |
|
"codebook_dim": 256, |
|
"codebook_size": 512, |
|
"decay": 0.99, |
|
"dim": 1280, |
|
"kmeans_init": true, |
|
"kmeans_iters": 100, |
|
"num_quantizers": 4, |
|
"quantize_dropout": true |
|
}, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "taste", |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"quantization_on": true, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"text_token_size": 51866, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": true, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": null, |
|
"torchscript": false, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"ignore_index": -100, |
|
"load_language_model_during_init": true, |
|
"model_type": "taste", |
|
"speech_decoder_config": { |
|
"_attn_implementation_autoset": false, |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"architectures": null, |
|
"audio_encoder_input_size": 1280, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder__attention_dropout_rate": 0, |
|
"encoder__attention_heads": 8, |
|
"encoder__dropout_rate": 0.1, |
|
"encoder__input_layer": "linear", |
|
"encoder__linear_units": 2048, |
|
"encoder__macaron_style": false, |
|
"encoder__normalize_before": true, |
|
"encoder__num_blocks": 3, |
|
"encoder__pos_enc_layer_type": "rel_pos_espnet", |
|
"encoder__positional_dropout_rate": 0.1, |
|
"encoder__selfattention_layer_type": "rel_selfattn", |
|
"encoder__static_chunk_size": 1, |
|
"encoder__use_cnn_module": false, |
|
"encoder__use_dynamic_chunk": false, |
|
"encoder__use_dynamic_left_chunk": false, |
|
"encoder_input_size": 512, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"fuse_encoded_audio_text_kwargs": { |
|
"normalize": false, |
|
"use_layer_norm": false, |
|
"use_trainable_weight": true, |
|
"weight_init_type": "balance" |
|
}, |
|
"fuse_encoded_audio_text_type": "weighted_sum", |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_normalized_loss": true, |
|
"length_penalty": 1.0, |
|
"llm__attention_dropout_rate": 0, |
|
"llm__attention_heads": 8, |
|
"llm__dropout_rate": 0.1, |
|
"llm__input_layer": "linear_legacy", |
|
"llm__linear_units": 2048, |
|
"llm__num_blocks": 7, |
|
"llm__pos_enc_layer_type": "rel_pos_espnet", |
|
"llm__positional_dropout_rate": 0.1, |
|
"llm__selfattention_layer_type": "rel_selfattn", |
|
"llm__static_chunk_size": 1, |
|
"llm_input_size": 1024, |
|
"llm_output_size": 1024, |
|
"lsm_weight": 0.0, |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "taste", |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"skip_prefix_idx": 4, |
|
"speech_token_size": 4096, |
|
"spk_embed_dim": 192, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"text_token_size": 51866, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": true, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": null, |
|
"torchscript": false, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false |
|
}, |
|
"spoken_lm_config": { |
|
"_attn_implementation_autoset": false, |
|
"_name_or_path": "", |
|
"add_cross_attention": false, |
|
"architectures": null, |
|
"audio_embed_conv_mode": "fill_forward", |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": null, |
|
"chunk_size_feed_forward": 0, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"delay": 1, |
|
"delay_level": "word", |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": null, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"in_llm_module": "weighted_sum", |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_penalty": 1.0, |
|
"loss_weights": "0.5-0.5", |
|
"max_length": 20, |
|
"min_length": 0, |
|
"model_type": "taste", |
|
"no_repeat_ngram_size": 0, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_return_sequences": 1, |
|
"out_llm_module": "continue_latent_linear_last", |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"prefix": null, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"sep_token_id": null, |
|
"sos_id": 128000, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": true, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": null, |
|
"torchscript": false, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"use_lora": true, |
|
"kwargs_for_lora": { |
|
"lora_model_dir": null, |
|
"lora_r": 64, |
|
"lora_alpha": 128, |
|
"lora_dropout": 0.05, |
|
"lora_target_linear": true, |
|
"lora_target_modules": null, |
|
"lora_fan_in_fan_out": null, |
|
"lora_modules_to_save": null |
|
} |
|
}, |
|
"text_config": { |
|
"_attn_implementation_autoset": false, |
|
"_name_or_path": "meta-llama/Llama-3.2-1B", |
|
"add_cross_attention": false, |
|
"architectures": [ |
|
"LlamaForCausalLM" |
|
], |
|
"attention_bias": false, |
|
"attention_dropout": 0.0, |
|
"bad_words_ids": null, |
|
"begin_suppress_tokens": null, |
|
"bos_token_id": 128000, |
|
"chunk_size_feed_forward": 0, |
|
"cross_attention_hidden_size": null, |
|
"decoder_start_token_id": null, |
|
"diversity_penalty": 0.0, |
|
"do_sample": false, |
|
"early_stopping": false, |
|
"encoder_no_repeat_ngram_size": 0, |
|
"eos_token_id": 128001, |
|
"exponential_decay_length_penalty": null, |
|
"finetuning_task": null, |
|
"forced_bos_token_id": null, |
|
"forced_eos_token_id": null, |
|
"head_dim": 64, |
|
"hidden_act": "silu", |
|
"hidden_size": 2048, |
|
"id2label": { |
|
"0": "LABEL_0", |
|
"1": "LABEL_1" |
|
}, |
|
"initializer_range": 0.02, |
|
"intermediate_size": 8192, |
|
"is_decoder": false, |
|
"is_encoder_decoder": false, |
|
"label2id": { |
|
"LABEL_0": 0, |
|
"LABEL_1": 1 |
|
}, |
|
"length_penalty": 1.0, |
|
"max_length": 20, |
|
"max_position_embeddings": 131072, |
|
"min_length": 0, |
|
"mlp_bias": false, |
|
"model_type": "llama", |
|
"no_repeat_ngram_size": 0, |
|
"num_attention_heads": 32, |
|
"num_beam_groups": 1, |
|
"num_beams": 1, |
|
"num_hidden_layers": 16, |
|
"num_key_value_heads": 8, |
|
"num_return_sequences": 1, |
|
"output_attentions": false, |
|
"output_hidden_states": false, |
|
"output_scores": false, |
|
"pad_token_id": null, |
|
"prefix": null, |
|
"pretraining_tp": 1, |
|
"problem_type": null, |
|
"pruned_heads": {}, |
|
"remove_invalid_values": false, |
|
"repetition_penalty": 1.0, |
|
"return_dict": true, |
|
"return_dict_in_generate": false, |
|
"rms_norm_eps": 1e-05, |
|
"rope_scaling": { |
|
"factor": 32.0, |
|
"high_freq_factor": 4.0, |
|
"low_freq_factor": 1.0, |
|
"original_max_position_embeddings": 8192, |
|
"rope_type": "llama3" |
|
}, |
|
"rope_theta": 500000.0, |
|
"sep_token_id": null, |
|
"suppress_tokens": null, |
|
"task_specific_params": null, |
|
"temperature": 1.0, |
|
"tf_legacy_loss": false, |
|
"tie_encoder_decoder": false, |
|
"tie_word_embeddings": true, |
|
"tokenizer_class": null, |
|
"top_k": 50, |
|
"top_p": 1.0, |
|
"torch_dtype": "bfloat16", |
|
"torchscript": false, |
|
"typical_p": 1.0, |
|
"use_bfloat16": false, |
|
"use_cache": true, |
|
"vocab_size": 128256 |
|
}, |
|
"_attn_implementation": "eager", |
|
"torch_dtype": "bfloat16", |
|
"transformers_version": "4.46.0" |
|
} |
|
|