Team Ai
Modelpublic

hf-tiny-model-private/tiny-random-SpeechEncoderDecoderModel-wav2vec2-bert

sourceHugging Faceupdated 4y agoView on Hugging Face
0likes31downloads
config.json234 linesDownload Raw Back to root
1{2  "_commit_hash": null,3  "architectures": [4    "SpeechEncoderDecoderModel"5  ],6  "decoder": {7    "_name_or_path": "/tmp/tmp6peh6iyp/decoder/BertLMHeadModel",8    "add_cross_attention": true,9    "architectures": [10      "BertLMHeadModel"11    ],12    "attention_probs_dropout_prob": 0.1,13    "bad_words_ids": null,14    "begin_suppress_tokens": null,15    "bos_token_id": null,16    "chunk_size_feed_forward": 0,17    "classifier_dropout": null,18    "cross_attention_hidden_size": null,19    "decoder_start_token_id": null,20    "diversity_penalty": 0.0,21    "do_sample": false,22    "early_stopping": false,23    "encoder_no_repeat_ngram_size": 0,24    "eos_token_id": null,25    "exponential_decay_length_penalty": null,26    "finetuning_task": null,27    "forced_bos_token_id": null,28    "forced_eos_token_id": null,29    "hidden_act": "gelu",30    "hidden_dropout_prob": 0.1,31    "hidden_size": 32,32    "id2label": {33      "0": "LABEL_0",34      "1": "LABEL_1"35    },36    "initializer_range": 0.02,37    "intermediate_size": 37,38    "is_decoder": true,39    "is_encoder_decoder": false,40    "label2id": {41      "LABEL_0": 0,42      "LABEL_1": 143    },44    "layer_norm_eps": 1e-12,45    "length_penalty": 1.0,46    "max_length": 20,47    "max_position_embeddings": 512,48    "min_length": 0,49    "model_type": "bert",50    "no_repeat_ngram_size": 0,51    "num_attention_heads": 4,52    "num_beam_groups": 1,53    "num_beams": 1,54    "num_hidden_layers": 5,55    "num_return_sequences": 1,56    "output_attentions": false,57    "output_hidden_states": false,58    "output_scores": false,59    "pad_token_id": 0,60    "position_embedding_type": "absolute",61    "prefix": null,62    "problem_type": null,63    "pruned_heads": {},64    "remove_invalid_values": false,65    "repetition_penalty": 1.0,66    "return_dict": true,67    "return_dict_in_generate": false,68    "sep_token_id": null,69    "suppress_tokens": null,70    "task_specific_params": null,71    "temperature": 1.0,72    "tf_legacy_loss": false,73    "tie_encoder_decoder": false,74    "tie_word_embeddings": true,75    "tokenizer_class": null,76    "top_k": 50,77    "top_p": 1.0,78    "torch_dtype": "float32",79    "torchscript": false,80    "transformers_version": "4.28.0.dev0",81    "type_vocab_size": 16,82    "typical_p": 1.0,83    "use_bfloat16": false,84    "use_cache": true,85    "vocab_size": 112486  },87  "encoder": {88    "_name_or_path": "/tmp/tmp6peh6iyp/encoder/Wav2Vec2Model",89    "activation_dropout": 0.1,90    "adapter_kernel_size": 3,91    "adapter_stride": 2,92    "add_adapter": false,93    "add_cross_attention": false,94    "apply_spec_augment": true,95    "architectures": [96      "Wav2Vec2Model"97    ],98    "attention_dropout": 0.1,99    "bad_words_ids": null,100    "begin_suppress_tokens": null,101    "bos_token_id": 1,102    "chunk_size_feed_forward": 0,103    "classifier_proj_size": 256,104    "codevector_dim": 256,105    "contrastive_logits_temperature": 0.1,106    "conv_bias": false,107    "conv_dim": [108      32,109      32,110      32111    ],112    "conv_kernel": [113      8,114      8,115      8116    ],117    "conv_stride": [118      4,119      4,120      4121    ],122    "cross_attention_hidden_size": null,123    "ctc_loss_reduction": "sum",124    "ctc_zero_infinity": false,125    "decoder_start_token_id": null,126    "diversity_loss_weight": 0.1,127    "diversity_penalty": 0.0,128    "do_sample": false,129    "do_stable_layer_norm": false,130    "early_stopping": false,131    "encoder_no_repeat_ngram_size": 0,132    "eos_token_id": 2,133    "exponential_decay_length_penalty": null,134    "feat_extract_activation": "gelu",135    "feat_extract_dropout": 0.0,136    "feat_extract_norm": "group",137    "feat_proj_dropout": 0.0,138    "feat_quantizer_dropout": 0.0,139    "final_dropout": 0.1,140    "finetuning_task": null,141    "forced_bos_token_id": null,142    "forced_eos_token_id": null,143    "hidden_act": "gelu",144    "hidden_dropout": 0.1,145    "hidden_dropout_prob": 0.1,146    "hidden_size": 16,147    "id2label": {148      "0": "LABEL_0",149      "1": "LABEL_1"150    },151    "initializer_range": 0.02,152    "intermediate_size": 20,153    "is_decoder": false,154    "is_encoder_decoder": false,155    "label2id": {156      "LABEL_0": 0,157      "LABEL_1": 1158    },159    "layer_norm_eps": 1e-05,160    "layerdrop": 0.1,161    "length_penalty": 1.0,162    "mask_feature_length": 10,163    "mask_feature_min_masks": 0,164    "mask_feature_prob": 0.0,165    "mask_time_length": 2,166    "mask_time_min_masks": 2,167    "mask_time_prob": 0.5,168    "max_length": 20,169    "min_length": 0,170    "model_type": "wav2vec2",171    "no_repeat_ngram_size": 0,172    "num_adapter_layers": 1,173    "num_attention_heads": 2,174    "num_beam_groups": 1,175    "num_beams": 1,176    "num_codevector_groups": 2,177    "num_codevectors_per_group": 320,178    "num_conv_pos_embedding_groups": 2,179    "num_conv_pos_embeddings": 16,180    "num_feat_extract_layers": 3,181    "num_hidden_layers": 4,182    "num_negatives": 100,183    "num_return_sequences": 1,184    "output_attentions": false,185    "output_hidden_size": 16,186    "output_hidden_states": false,187    "output_scores": false,188    "pad_token_id": 0,189    "prefix": null,190    "problem_type": null,191    "proj_codevector_dim": 256,192    "pruned_heads": {},193    "remove_invalid_values": false,194    "repetition_penalty": 1.0,195    "return_dict": true,196    "return_dict_in_generate": false,197    "sep_token_id": null,198    "suppress_tokens": null,199    "task_specific_params": null,200    "tdnn_dilation": [201      1,202      2203    ],204    "tdnn_dim": [205      32,206      32207    ],208    "tdnn_kernel": [209      5,210      3211    ],212    "temperature": 1.0,213    "tf_legacy_loss": false,214    "tie_encoder_decoder": false,215    "tie_word_embeddings": true,216    "tokenizer_class": null,217    "top_k": 50,218    "top_p": 1.0,219    "torch_dtype": "float32",220    "torchscript": false,221    "transformers_version": "4.28.0.dev0",222    "typical_p": 1.0,223    "use_bfloat16": false,224    "use_weighted_layer_sum": false,225    "vocab_size": 32,226    "xvector_output_dim": 32227  },228  "is_encoder_decoder": true,229  "model_type": "speech-encoder-decoder",230  "tie_word_embeddings": false,231  "torch_dtype": "float32",232  "transformers_version": null233}234