File size: 7,550 Bytes
1b9475a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
{
"_name_or_path": "/mnt/matylda5/ipoloka/IS24_DeCRED/multidomain/normalised_data/ED_base/checkpoint-233632",
"architectures": [
"JointCTCAttentionEncoderDecoder"
],
"auto_map": {
"AutoConfig": "configuration_decred.JointCTCAttentionEncoderDecoderConfig",
"AutoModelForSpeechSeq2Seq": "modeling_decred.JointCTCAttentionEncoderDecoder"
},
"ctc_weight": 0.3,
"decoder": {
"_name_or_path": "Lakoc/gpt2_8l_512h",
"activation_function": "gelu_new",
"add_cross_attention": true,
"architectures": null,
"attn_pdrop": 0.1,
"bad_words_ids": null,
"begin_suppress_tokens": null,
"bos_token_id": 50256,
"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": 50256,
"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"
},
"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",
"n_embd": 512,
"n_head": 4,
"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_size": 512,
"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_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": "<class 'transformers.tokenization_utils_fast.PreTrainedTokenizerFast'>",
"torch_dtype": "float32",
"transformers_version": "4.39.3"
}
|