Commit
•
32abf1b
1
Parent(s):
e7e4f17
Training in progress, step 4502
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- config.json +246 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +1 -0
- training_args.bin +3 -0
.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 +1,246 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"SpeechMixEEDT5"
|
4 |
+
],
|
5 |
+
"decoder": {
|
6 |
+
"_name_or_path": "voidful/phoneme-mt5",
|
7 |
+
"add_cross_attention": true,
|
8 |
+
"architectures": [
|
9 |
+
"T5ForConditionalGeneration"
|
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": 1024,
|
16 |
+
"d_kv": 64,
|
17 |
+
"d_model": 512,
|
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": "t5",
|
46 |
+
"no_repeat_ngram_size": 0,
|
47 |
+
"num_beam_groups": 1,
|
48 |
+
"num_beams": 1,
|
49 |
+
"num_decoder_layers": 8,
|
50 |
+
"num_heads": 6,
|
51 |
+
"num_layers": 8,
|
52 |
+
"num_return_sequences": 1,
|
53 |
+
"output_attentions": false,
|
54 |
+
"output_hidden_states": false,
|
55 |
+
"output_scores": false,
|
56 |
+
"pad_token_id": 0,
|
57 |
+
"prefix": null,
|
58 |
+
"problem_type": null,
|
59 |
+
"pruned_heads": {},
|
60 |
+
"relative_attention_max_distance": 128,
|
61 |
+
"relative_attention_num_buckets": 32,
|
62 |
+
"remove_invalid_values": false,
|
63 |
+
"repetition_penalty": 1.0,
|
64 |
+
"return_dict": true,
|
65 |
+
"return_dict_in_generate": false,
|
66 |
+
"sep_token_id": null,
|
67 |
+
"task_specific_params": null,
|
68 |
+
"temperature": 1.0,
|
69 |
+
"tie_encoder_decoder": false,
|
70 |
+
"tie_word_embeddings": false,
|
71 |
+
"tokenizer_class": "T5Tokenizer",
|
72 |
+
"top_k": 50,
|
73 |
+
"top_p": 1.0,
|
74 |
+
"torch_dtype": "bfloat16",
|
75 |
+
"torchscript": false,
|
76 |
+
"transformers_version": "4.18.0",
|
77 |
+
"typical_p": 1.0,
|
78 |
+
"use_bfloat16": false,
|
79 |
+
"use_cache": true,
|
80 |
+
"vocab_size": 250112
|
81 |
+
},
|
82 |
+
"encoder": {
|
83 |
+
"_name_or_path": "facebook/wav2vec2-large-lv60",
|
84 |
+
"activation_dropout": 0.1,
|
85 |
+
"adapter_kernel_size": 3,
|
86 |
+
"adapter_stride": 2,
|
87 |
+
"add_adapter": false,
|
88 |
+
"add_cross_attention": false,
|
89 |
+
"apply_spec_augment": true,
|
90 |
+
"architectures": [
|
91 |
+
"Wav2Vec2ForPreTraining"
|
92 |
+
],
|
93 |
+
"attention_dropout": 0.1,
|
94 |
+
"bad_words_ids": null,
|
95 |
+
"bos_token_id": 1,
|
96 |
+
"chunk_size_feed_forward": 0,
|
97 |
+
"classifier_proj_size": 256,
|
98 |
+
"codevector_dim": 768,
|
99 |
+
"contrastive_logits_temperature": 0.1,
|
100 |
+
"conv_bias": true,
|
101 |
+
"conv_dim": [
|
102 |
+
512,
|
103 |
+
512,
|
104 |
+
512,
|
105 |
+
512,
|
106 |
+
512,
|
107 |
+
512,
|
108 |
+
512
|
109 |
+
],
|
110 |
+
"conv_kernel": [
|
111 |
+
10,
|
112 |
+
3,
|
113 |
+
3,
|
114 |
+
3,
|
115 |
+
3,
|
116 |
+
2,
|
117 |
+
2
|
118 |
+
],
|
119 |
+
"conv_stride": [
|
120 |
+
5,
|
121 |
+
2,
|
122 |
+
2,
|
123 |
+
2,
|
124 |
+
2,
|
125 |
+
2,
|
126 |
+
2
|
127 |
+
],
|
128 |
+
"cross_attention_hidden_size": null,
|
129 |
+
"ctc_loss_reduction": "sum",
|
130 |
+
"ctc_zero_infinity": false,
|
131 |
+
"decoder_start_token_id": null,
|
132 |
+
"diversity_loss_weight": 0.1,
|
133 |
+
"diversity_penalty": 0.0,
|
134 |
+
"do_sample": false,
|
135 |
+
"do_stable_layer_norm": true,
|
136 |
+
"early_stopping": false,
|
137 |
+
"encoder_no_repeat_ngram_size": 0,
|
138 |
+
"eos_token_id": 2,
|
139 |
+
"exponential_decay_length_penalty": null,
|
140 |
+
"feat_extract_activation": "gelu",
|
141 |
+
"feat_extract_dropout": 0.0,
|
142 |
+
"feat_extract_norm": "layer",
|
143 |
+
"feat_proj_dropout": 0.1,
|
144 |
+
"feat_quantizer_dropout": 0.0,
|
145 |
+
"final_dropout": 0.1,
|
146 |
+
"finetuning_task": null,
|
147 |
+
"forced_bos_token_id": null,
|
148 |
+
"forced_eos_token_id": null,
|
149 |
+
"gradient_checkpointing": false,
|
150 |
+
"hidden_act": "gelu",
|
151 |
+
"hidden_dropout": 0.1,
|
152 |
+
"hidden_dropout_prob": 0.1,
|
153 |
+
"hidden_size": 1024,
|
154 |
+
"id2label": {
|
155 |
+
"0": "LABEL_0",
|
156 |
+
"1": "LABEL_1"
|
157 |
+
},
|
158 |
+
"initializer_range": 0.02,
|
159 |
+
"intermediate_size": 4096,
|
160 |
+
"is_decoder": false,
|
161 |
+
"is_encoder_decoder": false,
|
162 |
+
"label2id": {
|
163 |
+
"LABEL_0": 0,
|
164 |
+
"LABEL_1": 1
|
165 |
+
},
|
166 |
+
"layer_norm_eps": 1e-05,
|
167 |
+
"layerdrop": 0.0,
|
168 |
+
"length_penalty": 1.0,
|
169 |
+
"mask_feature_length": 10,
|
170 |
+
"mask_feature_min_masks": 0,
|
171 |
+
"mask_feature_prob": 0.0,
|
172 |
+
"mask_time_length": 10,
|
173 |
+
"mask_time_min_masks": 2,
|
174 |
+
"mask_time_prob": 0.05,
|
175 |
+
"max_length": 20,
|
176 |
+
"min_length": 0,
|
177 |
+
"model_type": "wav2vec2",
|
178 |
+
"no_repeat_ngram_size": 0,
|
179 |
+
"num_adapter_layers": 3,
|
180 |
+
"num_attention_heads": 16,
|
181 |
+
"num_beam_groups": 1,
|
182 |
+
"num_beams": 1,
|
183 |
+
"num_codevector_groups": 2,
|
184 |
+
"num_codevectors_per_group": 320,
|
185 |
+
"num_conv_pos_embedding_groups": 16,
|
186 |
+
"num_conv_pos_embeddings": 128,
|
187 |
+
"num_feat_extract_layers": 7,
|
188 |
+
"num_hidden_layers": 24,
|
189 |
+
"num_negatives": 100,
|
190 |
+
"num_return_sequences": 1,
|
191 |
+
"output_attentions": false,
|
192 |
+
"output_hidden_size": 1024,
|
193 |
+
"output_hidden_states": false,
|
194 |
+
"output_scores": false,
|
195 |
+
"pad_token_id": 0,
|
196 |
+
"prefix": null,
|
197 |
+
"problem_type": null,
|
198 |
+
"proj_codevector_dim": 768,
|
199 |
+
"pruned_heads": {},
|
200 |
+
"remove_invalid_values": false,
|
201 |
+
"repetition_penalty": 1.0,
|
202 |
+
"return_dict": true,
|
203 |
+
"return_dict_in_generate": false,
|
204 |
+
"sep_token_id": null,
|
205 |
+
"task_specific_params": null,
|
206 |
+
"tdnn_dilation": [
|
207 |
+
1,
|
208 |
+
2,
|
209 |
+
3,
|
210 |
+
1,
|
211 |
+
1
|
212 |
+
],
|
213 |
+
"tdnn_dim": [
|
214 |
+
512,
|
215 |
+
512,
|
216 |
+
512,
|
217 |
+
512,
|
218 |
+
1500
|
219 |
+
],
|
220 |
+
"tdnn_kernel": [
|
221 |
+
5,
|
222 |
+
3,
|
223 |
+
3,
|
224 |
+
1,
|
225 |
+
1
|
226 |
+
],
|
227 |
+
"temperature": 1.0,
|
228 |
+
"tie_encoder_decoder": false,
|
229 |
+
"tie_word_embeddings": true,
|
230 |
+
"tokenizer_class": null,
|
231 |
+
"top_k": 50,
|
232 |
+
"top_p": 1.0,
|
233 |
+
"torch_dtype": null,
|
234 |
+
"torchscript": false,
|
235 |
+
"transformers_version": "4.18.0",
|
236 |
+
"typical_p": 1.0,
|
237 |
+
"use_bfloat16": false,
|
238 |
+
"use_weighted_layer_sum": false,
|
239 |
+
"vocab_size": 32,
|
240 |
+
"xvector_output_dim": 512
|
241 |
+
},
|
242 |
+
"is_encoder_decoder": true,
|
243 |
+
"model_type": "speechmix",
|
244 |
+
"torch_dtype": "float32",
|
245 |
+
"transformers_version": null
|
246 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ab4f94bd2a1ac903f9299b5b356ee03073f590205871a526a0bd617ff57eaa3
|
3 |
+
size 2489955239
|
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/twskvfb446/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-small", "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 sha256:46ceb93faab410daca077c7e53628d737a08b160dd7492c11fcc713e46e571d2
|
3 |
+
size 3375
|