{ "_name_or_path": "BUT-FIT/DeCRED-base", "architectures": [ "JointCTCAttentionEncoderDecoder" ], "auto_map": { "AutoConfig": "BUT-FIT/DeCRED-base--configuration_decred.JointCTCAttentionEncoderDecoderConfig", "AutoModelForSpeechSeq2Seq": "BUT-FIT/DeCRED-base--modeling_decred.JointCTCAttentionEncoderDecoder" }, "ctc_weight": 0.3, "decoder": { "_name_or_path": "Lakoc/gpt2_512h_8l_add_head6_04", "activation_function": "gelu_new", "add_cross_attention": true, "architectures": null, "attn_pdrop": 0.1, "average_logits": false, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 0, "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, "embd_pdrop": 0.1, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 1, "exponential_decay_length_penalty": null, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "head_locations": [ 5 ], "head_weights": [ 0.6, 0.4 ], "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "is_decoder": true, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_epsilon": 1e-05, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "gpt2-multi-head", "n_embd": 512, "n_head": 8, "n_inner": 2048, "n_layer": 8, "n_positions": 1024, "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, "pos_emb_fixed": true, "prefix": null, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "reorder_and_upcast_attn": false, "repetition_penalty": 1.0, "resid_pdrop": 0.1, "return_dict": true, "return_dict_in_generate": false, "scale_attn_by_inverse_layer_idx": false, "scale_attn_weights": true, "sep_token_id": null, "summary_activation": null, "summary_first_dropout": 0.1, "summary_proj_to_labels": true, "summary_type": "cls_index", "summary_use_proj": true, "suppress_tokens": null, "task_specific_params": null, "temperature": 1.0, "tf_legacy_loss": false, "tie_additional_weights": false, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_cache": true, "vocab_size": 5000 }, "decoder_pos_emb_fixed": true, "decoder_start_token_id": 0, "decoder_vocab_size": 5000, "encoder": { "_name_or_path": "Lakoc/ebranchformer_16l_512h", "activation_dropout": 0.1, "adapter_attn_dim": null, "adapter_kernel_size": 3, "adapter_stride": 2, "add_adapter": false, "add_cross_attention": false, "apply_spec_augment": false, "apply_time_warp": false, "architectures": null, "attention_dropout": 0.1, "bad_words_ids": null, "begin_suppress_tokens": null, "bos_token_id": 1, "chunk_size_feed_forward": 0, "classifier_proj_size": 256, "codevector_dim": 256, "conformer_conv_dropout": 0.1, "contrastive_logits_temperature": 0.1, "conv_bias": false, "conv_depthwise_kernel_size": 31, "conv_dim": [ 512, 512 ], "conv_kernel": [ 3, 3 ], "conv_stride": [ 2, 2 ], "cross_attention_hidden_size": null, "csgu_activation": "identity", "csgu_conv_dropout": 0.1, "csgu_kernel_size": 31, "csgu_use_linear_after_conv": false, "ctc_loss_reduction": "mean", "ctc_zero_infinity": true, "decoder_start_token_id": null, "diversity_loss_weight": 0.1, "diversity_penalty": 0.0, "do_sample": false, "do_stable_layer_norm": false, "early_stopping": false, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "expect_2d_input": true, "exponential_decay_length_penalty": null, "fe_position_embeddings": true, "feat_extract_activation": "gelu", "feat_extract_norm": "group", "feat_proj_dropout": 0.0, "feat_quantizer_dropout": 0.0, "final_dropout": 0.1, "finetuning_task": null, "forced_bos_token_id": null, "forced_eos_token_id": null, "hidden_act": "gelu", "hidden_dropout": 0.1, "hidden_size": 512, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "intermediate_size": 2048, "is_causal": false, "is_decoder": false, "is_encoder_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "layer_norm_eps": 1e-05, "layerdrop": 0.0, "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": 20, "max_source_positions": 1024, "merge_conv_kernel": 31, "min_length": 0, "model_type": "wav2vec2-ebranchformer", "no_repeat_ngram_size": 0, "num_adapter_layers": 3, "num_attention_heads": 4, "num_beam_groups": 1, "num_beams": 1, "num_codevector_groups": 2, "num_codevectors_per_group": 320, "num_conv_pos_embedding_groups": 16, "num_conv_pos_embeddings": 128, "num_feat_extract_layers": 2, "num_hidden_layers": 16, "num_mel_bins": 80, "num_negatives": 100, "num_return_sequences": 1, "output_attentions": false, "output_hidden_size": 512, "output_hidden_states": false, "output_scores": false, "pad_token_id": 3, "position_embeddings_type": "relative", "prefix": null, "problem_type": null, "proj_codevector_dim": 256, "pruned_heads": {}, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "rotary_embedding_base": 10000, "second_dim_input_size": 80, "sep_token_id": null, "suppress_tokens": null, "task_specific_params": null, "tdnn_dilation": [ 1, 2, 3, 1, 1 ], "tdnn_dim": [ 512, 512, 512, 512, 1500 ], "tdnn_kernel": [ 5, 3, 3, 1, 1 ], "temperature": 1.0, "tf_legacy_loss": false, "tie_encoder_decoder": false, "tie_word_embeddings": true, "time_warp_mode": "bicubic", "time_warp_window": 5, "tokenizer_class": null, "top_k": 50, "top_p": 1.0, "torch_dtype": null, "torchscript": false, "typical_p": 1.0, "use_bfloat16": false, "use_fbanks": true, "use_macaron_ff": true, "use_weighted_layer_sum": false, "vocab_size": 5000, "xvector_output_dim": 512 }, "encoder_ctc_loss_reduction": "mean", "encoder_expect_2d_input": true, "encoder_layerdrop": 0.0, "encoder_pad_token_id": 3, "encoder_second_dim_input_size": 80, "encoder_vocab_size": 5000, "is_encoder_decoder": true, "lsm_factor": 0.1, "model_type": "joint_aed_ctc_speech-encoder-decoder", "pad_token_id": 3, "shared_lm_head": false, "tie_word_embeddings": false, "tokenizer_class": "", "torch_dtype": "float32", "transformers_version": "4.39.3" }