WavEmbed-50 / config.json
charsiu's picture
Upload 3 files
06e764f
{
"architectures": [
"SpeechEncoderDecoderModel"
],
"decoder": {
"_name_or_path": "/gpfs/accounts/lingjzhu_root/lingjzhu1/lingjzhu/embeddings/models/bert-hubert-50/checkpoint-32000",
"add_cross_attention": true,
"architectures": [
"BertForMaskedLM"
],
"attention_probs_dropout_prob": 0.1,
"bad_words_ids": null,
"bos_token_id": null,
"chunk_size_feed_forward": 0,
"classifier_dropout": null,
"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": null,
"exponential_decay_length_penalty": null,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": true,
"is_encoder_decoder": false,
"label2id": {
"LABEL_0": 0,
"LABEL_1": 1
},
"layer_norm_eps": 1e-12,
"length_penalty": 1.0,
"max_length": 20,
"max_position_embeddings": 512,
"min_length": 0,
"model_type": "bert",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"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,
"task_specific_params": null,
"temperature": 1.0,
"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": "4.18.0",
"type_vocab_size": 2,
"typical_p": 1.0,
"use_bfloat16": false,
"use_cache": true,
"vocab_size": 55
},
"decoder_start_token_id": 54,
"encoder": {
"_name_or_path": "facebook/hubert-base-ls960",
"activation_dropout": 0.1,
"add_cross_attention": false,
"apply_spec_augment": true,
"architectures": [
"HubertModel"
],
"attention_dropout": 0.1,
"bad_words_ids": null,
"bos_token_id": 1,
"chunk_size_feed_forward": 0,
"classifier_proj_size": 256,
"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_penalty": 0.0,
"do_sample": false,
"do_stable_layer_norm": false,
"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": "group",
"feat_proj_dropout": 0.1,
"feat_proj_layer_norm": true,
"final_dropout": 0.1,
"finetuning_task": null,
"forced_bos_token_id": null,
"forced_eos_token_id": null,
"gradient_checkpointing": false,
"hidden_act": "gelu",
"hidden_dropout": 0.1,
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "LABEL_0",
"1": "LABEL_1"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"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_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,
"min_length": 0,
"model_type": "hubert",
"no_repeat_ngram_size": 0,
"num_attention_heads": 12,
"num_beam_groups": 1,
"num_beams": 1,
"num_conv_pos_embedding_groups": 16,
"num_conv_pos_embeddings": 128,
"num_feat_extract_layers": 7,
"num_hidden_layers": 12,
"num_return_sequences": 1,
"output_attentions": false,
"output_hidden_states": false,
"output_scores": false,
"pad_token_id": 0,
"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,
"task_specific_params": null,
"temperature": 1.0,
"tie_encoder_decoder": false,
"tie_word_embeddings": true,
"tokenizer_class": "Wav2Vec2CTCTokenizer",
"top_k": 50,
"top_p": 1.0,
"torch_dtype": null,
"torchscript": false,
"transformers_version": "4.18.0",
"typical_p": 1.0,
"use_bfloat16": false,
"use_weighted_layer_sum": false,
"vocab_size": 32
},
"is_encoder_decoder": true,
"model_type": "speech-encoder-decoder",
"pad_token_id": 52,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": null,
"vocab_size": 55
}