Splend1dchan commited on
Commit
dc928b7
1 Parent(s): bb427a1

Training in progress, step 4502

Browse files
.gitattributes CHANGED
@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,247 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "SpeechMixEEDT5"
4
+ ],
5
+ "decoder": {
6
+ "_name_or_path": "google/mt5-base",
7
+ "add_cross_attention": true,
8
+ "architectures": [
9
+ "MT5ForConditionalGeneration"
10
+ ],
11
+ "bad_words_ids": null,
12
+ "bos_token_id": null,
13
+ "chunk_size_feed_forward": 0,
14
+ "cross_attention_hidden_size": null,
15
+ "d_ff": 2048,
16
+ "d_kv": 64,
17
+ "d_model": 768,
18
+ "decoder_start_token_id": 0,
19
+ "diversity_penalty": 0.0,
20
+ "do_sample": false,
21
+ "dropout_rate": 0.1,
22
+ "early_stopping": false,
23
+ "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 1,
25
+ "exponential_decay_length_penalty": null,
26
+ "feed_forward_proj": "gated-gelu",
27
+ "finetuning_task": null,
28
+ "forced_bos_token_id": null,
29
+ "forced_eos_token_id": null,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1"
33
+ },
34
+ "initializer_factor": 1.0,
35
+ "is_decoder": true,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1
40
+ },
41
+ "layer_norm_epsilon": 1e-06,
42
+ "length_penalty": 1.0,
43
+ "max_length": 20,
44
+ "min_length": 0,
45
+ "model_type": "mt5",
46
+ "no_repeat_ngram_size": 0,
47
+ "num_beam_groups": 1,
48
+ "num_beams": 1,
49
+ "num_decoder_layers": 12,
50
+ "num_heads": 12,
51
+ "num_layers": 12,
52
+ "num_return_sequences": 1,
53
+ "output_attentions": false,
54
+ "output_hidden_states": false,
55
+ "output_past": true,
56
+ "output_scores": false,
57
+ "pad_token_id": 0,
58
+ "prefix": null,
59
+ "problem_type": null,
60
+ "pruned_heads": {},
61
+ "relative_attention_max_distance": 128,
62
+ "relative_attention_num_buckets": 32,
63
+ "remove_invalid_values": false,
64
+ "repetition_penalty": 1.0,
65
+ "return_dict": true,
66
+ "return_dict_in_generate": false,
67
+ "sep_token_id": null,
68
+ "task_specific_params": null,
69
+ "temperature": 1.0,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": false,
72
+ "tokenizer_class": "T5Tokenizer",
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": null,
76
+ "torchscript": false,
77
+ "transformers_version": "4.18.0",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "use_cache": true,
81
+ "vocab_size": 250112
82
+ },
83
+ "encoder": {
84
+ "_name_or_path": "facebook/wav2vec2-large-lv60",
85
+ "activation_dropout": 0.1,
86
+ "adapter_kernel_size": 3,
87
+ "adapter_stride": 2,
88
+ "add_adapter": false,
89
+ "add_cross_attention": false,
90
+ "apply_spec_augment": true,
91
+ "architectures": [
92
+ "Wav2Vec2ForPreTraining"
93
+ ],
94
+ "attention_dropout": 0.1,
95
+ "bad_words_ids": null,
96
+ "bos_token_id": 1,
97
+ "chunk_size_feed_forward": 0,
98
+ "classifier_proj_size": 256,
99
+ "codevector_dim": 768,
100
+ "contrastive_logits_temperature": 0.1,
101
+ "conv_bias": true,
102
+ "conv_dim": [
103
+ 512,
104
+ 512,
105
+ 512,
106
+ 512,
107
+ 512,
108
+ 512,
109
+ 512
110
+ ],
111
+ "conv_kernel": [
112
+ 10,
113
+ 3,
114
+ 3,
115
+ 3,
116
+ 3,
117
+ 2,
118
+ 2
119
+ ],
120
+ "conv_stride": [
121
+ 5,
122
+ 2,
123
+ 2,
124
+ 2,
125
+ 2,
126
+ 2,
127
+ 2
128
+ ],
129
+ "cross_attention_hidden_size": null,
130
+ "ctc_loss_reduction": "sum",
131
+ "ctc_zero_infinity": false,
132
+ "decoder_start_token_id": null,
133
+ "diversity_loss_weight": 0.1,
134
+ "diversity_penalty": 0.0,
135
+ "do_sample": false,
136
+ "do_stable_layer_norm": true,
137
+ "early_stopping": false,
138
+ "encoder_no_repeat_ngram_size": 0,
139
+ "eos_token_id": 2,
140
+ "exponential_decay_length_penalty": null,
141
+ "feat_extract_activation": "gelu",
142
+ "feat_extract_dropout": 0.0,
143
+ "feat_extract_norm": "layer",
144
+ "feat_proj_dropout": 0.1,
145
+ "feat_quantizer_dropout": 0.0,
146
+ "final_dropout": 0.1,
147
+ "finetuning_task": null,
148
+ "forced_bos_token_id": null,
149
+ "forced_eos_token_id": null,
150
+ "gradient_checkpointing": false,
151
+ "hidden_act": "gelu",
152
+ "hidden_dropout": 0.1,
153
+ "hidden_dropout_prob": 0.1,
154
+ "hidden_size": 1024,
155
+ "id2label": {
156
+ "0": "LABEL_0",
157
+ "1": "LABEL_1"
158
+ },
159
+ "initializer_range": 0.02,
160
+ "intermediate_size": 4096,
161
+ "is_decoder": false,
162
+ "is_encoder_decoder": false,
163
+ "label2id": {
164
+ "LABEL_0": 0,
165
+ "LABEL_1": 1
166
+ },
167
+ "layer_norm_eps": 1e-05,
168
+ "layerdrop": 0.0,
169
+ "length_penalty": 1.0,
170
+ "mask_feature_length": 10,
171
+ "mask_feature_min_masks": 0,
172
+ "mask_feature_prob": 0.0,
173
+ "mask_time_length": 10,
174
+ "mask_time_min_masks": 2,
175
+ "mask_time_prob": 0.05,
176
+ "max_length": 20,
177
+ "min_length": 0,
178
+ "model_type": "wav2vec2",
179
+ "no_repeat_ngram_size": 0,
180
+ "num_adapter_layers": 3,
181
+ "num_attention_heads": 16,
182
+ "num_beam_groups": 1,
183
+ "num_beams": 1,
184
+ "num_codevector_groups": 2,
185
+ "num_codevectors_per_group": 320,
186
+ "num_conv_pos_embedding_groups": 16,
187
+ "num_conv_pos_embeddings": 128,
188
+ "num_feat_extract_layers": 7,
189
+ "num_hidden_layers": 24,
190
+ "num_negatives": 100,
191
+ "num_return_sequences": 1,
192
+ "output_attentions": false,
193
+ "output_hidden_size": 1024,
194
+ "output_hidden_states": false,
195
+ "output_scores": false,
196
+ "pad_token_id": 0,
197
+ "prefix": null,
198
+ "problem_type": null,
199
+ "proj_codevector_dim": 768,
200
+ "pruned_heads": {},
201
+ "remove_invalid_values": false,
202
+ "repetition_penalty": 1.0,
203
+ "return_dict": true,
204
+ "return_dict_in_generate": false,
205
+ "sep_token_id": null,
206
+ "task_specific_params": null,
207
+ "tdnn_dilation": [
208
+ 1,
209
+ 2,
210
+ 3,
211
+ 1,
212
+ 1
213
+ ],
214
+ "tdnn_dim": [
215
+ 512,
216
+ 512,
217
+ 512,
218
+ 512,
219
+ 1500
220
+ ],
221
+ "tdnn_kernel": [
222
+ 5,
223
+ 3,
224
+ 3,
225
+ 1,
226
+ 1
227
+ ],
228
+ "temperature": 1.0,
229
+ "tie_encoder_decoder": false,
230
+ "tie_word_embeddings": true,
231
+ "tokenizer_class": null,
232
+ "top_k": 50,
233
+ "top_p": 1.0,
234
+ "torch_dtype": null,
235
+ "torchscript": false,
236
+ "transformers_version": "4.18.0",
237
+ "typical_p": 1.0,
238
+ "use_bfloat16": false,
239
+ "use_weighted_layer_sum": false,
240
+ "vocab_size": 32,
241
+ "xvector_output_dim": 512
242
+ },
243
+ "is_encoder_decoder": true,
244
+ "model_type": "speechmix",
245
+ "torch_dtype": "float32",
246
+ "transformers_version": null
247
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701341ea0e8bb3949f83fe0bfd0c7845c08a2d11eed96c120270b41d0d581855
3
+ size 3619935535
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
3
+ size 4309802
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
3
+ size 16330369
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec58b2cb250ba7dce5159554b7e5c5633e5fd9d6c88e5c207c76cf2132cd2e6d
3
+ size 3311