robustspeech-asr / config.json
nguyenvulebinh's picture
Upload model
c3b30b7
{
"_name_or_path": "/export/data1/data/binhnguyen/workspaces/robustspeech/model-bin/asr/wavlm-large_bart-base-deepfilter-word_align_augment_with_noise/avg",
"architectures": [
"SEASRModel"
],
"asr_config": {
"_commit_hash": null,
"_name_or_path": "",
"add_cross_attention": false,
"architectures": null,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"cross_attention_hidden_size": null,
"decoder": {
"_name_or_path": "facebook/bart-base",
"activation_dropout": 0.1,
"activation_function": "gelu",
"add_bias_logits": false,
"add_cross_attention": true,
"add_final_layer_norm": false,
"architectures": [
"BartModel"
],
"attention_dropout": 0.1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 0,
"chunk_size_feed_forward": 0,
"classif_dropout": 0.1,
"classifier_dropout": 0.0,
"cross_attention_hidden_size": null,
"d_model": 768,
"decoder_attention_heads": 12,
"decoder_ffn_dim": 3072,
"decoder_layerdrop": 0.0,
"decoder_layers": 6,
"decoder_start_token_id": 2,
"diversity_penalty": 0.0,
"do_sample": false,
"dropout": 0.1,
"early_stopping": true,
"encoder_attention_heads": 12,
"encoder_ffn_dim": 3072,
"encoder_layerdrop": 0.0,
"encoder_layers": 6,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": 0,
"forced_eos_token_id": 2,
"gradient_checkpointing": false,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1",
"2": "LABEL_2"
},
"init_std": 0.02,
"is_decoder": true,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1,
"LABEL_2": 2
},
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 1024,
"min_length": 0,
"model_type": "bart",
"no_repeat_ngram_size": 3,
"normalize_before": false,
"normalize_embedding": true,
"num_beam_groups": 1,
"num_beams": 4,
"num_hidden_layers": 6,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 1,
"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": {
"summarization": {
"length_penalty": 1.0,
"max_length": 128,
"min_length": 12,
"num_beams": 4
},
"summarization_cnn": {
"length_penalty": 2.0,
"max_length": 142,
"min_length": 56,
"num_beams": 4
},
"summarization_xsum": {
"length_penalty": 1.0,
"max_length": 62,
"min_length": 11,
"num_beams": 6
}
},
"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": "float32",
"torchscript": false,
"transformers_version": "4.28.1",
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 50265
},
"decoder_start_token_id": null,
"diversity_penalty": 0.0,
"do_sample": false,
"early_stopping": false,
"encoder": {
"_name_or_path": "microsoft/wavlm-large",
"activation_dropout": 0.0,
"adapter_kernel_size": 3,
"adapter_stride": 2,
"add_adapter": true,
"add_cross_attention": false,
"apply_spec_augment": true,
"architectures": [
"WavLMModel"
],
"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": 768,
"contrastive_logits_temperature": 0.1,
"conv_bias": false,
"conv_dim": [
512,
512,
512,
512,
512,
512,
512
],
"conv_kernel": [
10,
3,
3,
3,
3,
2,
2
],
"conv_stride": [
5,
2,
2,
2,
2,
2,
2
],
"cross_attention_hidden_size": null,
"ctc_loss_reduction": "sum",
"ctc_zero_infinity": false,
"decoder_start_token_id": null,
"diversity_loss_weight": 0.1,
"diversity_penalty": 0.0,
"do_sample": false,
"do_stable_layer_norm": true,
"early_stopping": false,
"encoder_no_repeat_ngram_size": 0,
"eos_token_id": 2,
"exponential_decay_length_penalty": null,
"feat_extract_activation": "gelu",
"feat_extract_dropout": 0.0,
"feat_extract_norm": "layer",
"feat_proj_dropout": 0.1,
"feat_quantizer_dropout": 0.0,
"final_dropout": 0.0,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_size": 1024,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 4096,
"is_decoder": false,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-05,
"layerdrop": 0.1,
"length_penalty": 1.0,
"mask_channel_length": 10,
"mask_channel_min_space": 1,
"mask_channel_other": 0.0,
"mask_channel_prob": 0.0,
"mask_channel_selection": "static",
"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_min_space": 1,
"mask_time_other": 0.0,
"mask_time_prob": 0.075,
"mask_time_selection": "static",
"max_bucket_distance": 800,
"max_length": 20,
"min_length": 0,
"model_type": "wavlm",
"no_repeat_ngram_size": 0,
"num_adapter_layers": 3,
"num_attention_heads": 16,
"num_beam_groups": 1,
"num_beams": 1,
"num_buckets": 320,
"num_codevector_groups": 2,
"num_codevectors_per_group": 320,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_ctc_classes": 80,
"num_feat_extract_layers": 7,
"num_hidden_layers": 24,
"num_negatives": 100,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_size": 1024,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 0,
"prefix": null,
"problem_type": null,
"proj_codevector_dim": 768,
"pruned_heads": {},
"remove_invalid_values": false,
"repetition_penalty": 1.0,
"replace_prob": 0.5,
"return_dict": true,
"return_dict_in_generate": false,
"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,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"top_k": 50,
"top_p": 1.0,
"torch_dtype": "float32",
"torchscript": false,
"transformers_version": "4.28.1",
"typical_p": 1.0,
"use_bfloat16": false,
"use_weighted_layer_sum": false,
"vocab_size": 32,
"xvector_output_dim": 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,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"is_decoder": false,
"is_encoder_decoder": true,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"length_penalty": 1.0,
"max_length": 20,
"min_length": 0,
"model_type": "speech-encoder-decoder",
"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,
"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,
"transformers_version": null,
"typical_p": 1.0,
"use_bfloat16": false
},
"encoder_add_adapter": true,
"max_timestamp": 20,
"model_type": "robustspeech",
"speech_decoder_id": "facebook/bart-base",
"speech_encoder_id": "microsoft/wavlm-large",
"speech_enhance_config": {
"deepfilternet": {
"conv_ch": "64",
"conv_dec_mode": "transposed",
"conv_depthwise": "True",
"conv_kernel": "1,3",
"conv_kernel_inp": "3,3",
"conv_lookahead": "2",
"convt_depthwise": "True",
"df_gru_skip": "none",
"df_hidden_dim": "256",
"df_lookahead": "2",
"df_n_iter": "1",
"df_num_layers": "2",
"df_order": "5",
"df_output_layer": "groupedlinear",
"df_pathway_kernel_size_t": "5",
"dfop_method": "df",
"emb_hidden_dim": "256",
"emb_num_layers": "3",
"enc_concat": "True",
"group_shuffle": "False",
"gru_groups": "8",
"gru_type": "squeeze",
"linear_groups": "8",
"mask_pf": "False"
},
"df": {
"fft_size": "960",
"hop_size": "480",
"lsnr_max": "35",
"lsnr_min": "-15",
"min_nb_erb_freqs": "2",
"nb_df": "96",
"nb_erb": "32",
"norm_tau": "1",
"pad_mode": "input_specf",
"sr": "48000"
},
"dfalphaloss": {
"factor": "0.0"
},
"localsnrloss": {
"factor": "1e-3"
},
"maskloss": {
"f_under": "1",
"factor": "0",
"gamma": "0.6",
"gamma_pred": "0.6",
"mask": "iam"
},
"multiresspecloss": {
"factor": "500",
"factor_complex": "500",
"fft_sizes": "256,512,1024",
"gamma": "0.3"
},
"optim": {
"lr": "0.001",
"lr_cycle_decay": "0.5",
"lr_cycle_epochs": "-1",
"lr_cycle_limit": "1",
"lr_cycle_mul": "1.0",
"lr_min": "1e-06",
"lr_update_per_epoch": "False",
"lr_warmup": "0.0001",
"momentum": "0",
"optimizer": "adamw",
"warmup_epochs": "3",
"weight_decay": "1e-12",
"weight_decay_end": "0.05"
},
"sdrloss": {
"factor": "0.0",
"segmental_ws": "0"
},
"spectralloss": {
"factor_complex": "1000",
"factor_magnitude": "1000",
"gamma": "0.3"
},
"train": {
"batch_size": "96",
"batch_size_eval": "128",
"batch_size_scheduling": "0/8,1/16,2/24,5/32,10/64,20/128,40/9999",
"dataloader_snrs": "-5,0,5,10,20,40",
"detect_anomaly": "false",
"device": "",
"df_only": "false",
"early_stopping_patience": "15",
"global_ds_sampling_f": "1",
"jit": "false",
"log_freq": "100",
"log_timings": "False",
"mask_only": "false",
"max_epochs": "100",
"max_sample_len_s": "3.0",
"model": "deepfilternet2",
"num_prefetch_batches": "8",
"num_workers": "16",
"overfit": "false",
"p_atten_lim": "0.0",
"p_reverb": "0.1",
"seed": "43",
"start_eval": "true",
"validation_criteria": "loss",
"validation_criteria_rule": "min",
"validation_set_caching": "false"
}
},
"timestamp_stride": 0.02,
"torch_dtype": "float32",
"transformers_version": "4.30.2"
}