Hugging Face's logo

kksukk
/
hubert_zeroth_gpu_scratch

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
hubert
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
1
kksukk commited on
Commit
5c0b1c1
·
1 Parent(s): 81b1640

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +284 -0
README.md ADDED
@@ -0,0 +1,284 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ datasets:
5
+ - zeroth_korean_asr
6
+ metrics:
7
+ - wer
8
+ model-index:
9
+ - name: hubert_zeroth_gpu_scratch
10
+ results:
11
+ - task:
12
+ name: Automatic Speech Recognition
13
+ type: automatic-speech-recognition
14
+ dataset:
15
+ name: zeroth_korean_asr
16
+ type: zeroth_korean_asr
17
+ config: clean
18
+ split: train
19
+ args: clean
20
+ metrics:
21
+ - name: Wer
22
+ type: wer
23
+ value: 1.0
24
+ ---
25
+
26
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
+ should probably proofread and complete it, then remove this comment. -->
28
+
29
+ # hubert_zeroth_gpu_scratch
30
+
31
+ This model is a fine-tuned version of [](https://huggingface.co/) on the zeroth_korean_asr dataset.
32
+ It achieves the following results on the evaluation set:
33
+ - Loss: 4.8280
34
+ - Wer: 1.0
35
+
36
+ ## Model description
37
+
38
+ More information needed
39
+
40
+ ## Intended uses & limitations
41
+
42
+ More information needed
43
+
44
+ ## Training and evaluation data
45
+
46
+ More information needed
47
+
48
+ ## Training procedure
49
+
50
+ ### Training hyperparameters
51
+
52
+ The following hyperparameters were used during training:
53
+ - learning_rate: 0.0003
54
+ - train_batch_size: 16
55
+ - eval_batch_size: 16
56
+ - seed: 42
57
+ - gradient_accumulation_steps: 2
58
+ - total_train_batch_size: 32
59
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
60
+ - lr_scheduler_type: linear
61
+ - lr_scheduler_warmup_steps: 500
62
+ - num_epochs: 30
63
+ - mixed_precision_training: Native AMP
64
+
65
+ ### Training results
66
+
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-----:|:-----:|:---------------:|:---:|
69
+ | 10.6349 | 0.14 | 100 | 4.8579 | 1.0 |
70
+ | 4.7539 | 0.29 | 200 | 4.7308 | 1.0 |
71
+ | 4.7255 | 0.43 | 300 | 4.7278 | 1.0 |
72
+ | 4.7124 | 0.57 | 400 | 5.3295 | 1.0 |
73
+ | 4.7543 | 0.72 | 500 | 4.7487 | 1.0 |
74
+ | 4.8932 | 0.86 | 600 | 4.9136 | 1.0 |
75
+ | 4.8533 | 1.01 | 700 | 4.8799 | 1.0 |
76
+ | 4.8483 | 1.15 | 800 | 4.8665 | 1.0 |
77
+ | 4.8424 | 1.29 | 900 | 4.8622 | 1.0 |
78
+ | 4.8426 | 1.44 | 1000 | 4.8506 | 1.0 |
79
+ | 4.8373 | 1.58 | 1100 | 4.8603 | 1.0 |
80
+ | 4.8452 | 1.72 | 1200 | 4.8537 | 1.0 |
81
+ | 4.8391 | 1.87 | 1300 | 4.8520 | 1.0 |
82
+ | 4.8405 | 2.01 | 1400 | 4.8682 | 1.0 |
83
+ | 4.8375 | 2.16 | 1500 | 4.8637 | 1.0 |
84
+ | 4.8413 | 2.3 | 1600 | 4.8664 | 1.0 |
85
+ | 4.8388 | 2.44 | 1700 | 4.8473 | 1.0 |
86
+ | 4.8389 | 2.59 | 1800 | 4.8484 | 1.0 |
87
+ | 4.8343 | 2.73 | 1900 | 4.8629 | 1.0 |
88
+ | 4.8294 | 2.87 | 2000 | 4.8571 | 1.0 |
89
+ | 4.827 | 3.02 | 2100 | 4.8472 | 1.0 |
90
+ | 4.8316 | 3.16 | 2200 | 4.8576 | 1.0 |
91
+ | 4.8241 | 3.3 | 2300 | 4.8398 | 1.0 |
92
+ | 4.8333 | 3.45 | 2400 | 4.8603 | 1.0 |
93
+ | 4.8387 | 3.59 | 2500 | 4.8484 | 1.0 |
94
+ | 4.8312 | 3.74 | 2600 | 4.8420 | 1.0 |
95
+ | 4.8304 | 3.88 | 2700 | 4.8398 | 1.0 |
96
+ | 4.8291 | 4.02 | 2800 | 4.8355 | 1.0 |
97
+ | 4.8326 | 4.17 | 2900 | 4.8415 | 1.0 |
98
+ | 4.8274 | 4.31 | 3000 | 4.8338 | 1.0 |
99
+ | 4.8245 | 4.45 | 3100 | 4.8389 | 1.0 |
100
+ | 4.83 | 4.6 | 3200 | 4.8332 | 1.0 |
101
+ | 4.8335 | 4.74 | 3300 | 4.8393 | 1.0 |
102
+ | 4.829 | 4.89 | 3400 | 4.8352 | 1.0 |
103
+ | 4.832 | 5.03 | 3500 | 4.8329 | 1.0 |
104
+ | 4.8285 | 5.17 | 3600 | 4.8343 | 1.0 |
105
+ | 4.8302 | 5.32 | 3700 | 4.8381 | 1.0 |
106
+ | 4.8371 | 5.46 | 3800 | 4.8426 | 1.0 |
107
+ | 4.8226 | 5.6 | 3900 | 4.8383 | 1.0 |
108
+ | 4.8257 | 5.75 | 4000 | 4.8372 | 1.0 |
109
+ | 4.8222 | 5.89 | 4100 | 4.8332 | 1.0 |
110
+ | 4.8255 | 6.03 | 4200 | 4.8437 | 1.0 |
111
+ | 4.8277 | 6.18 | 4300 | 4.8351 | 1.0 |
112
+ | 4.8257 | 6.32 | 4400 | 4.8368 | 1.0 |
113
+ | 4.8301 | 6.47 | 4500 | 4.8345 | 1.0 |
114
+ | 4.8267 | 6.61 | 4600 | 4.8343 | 1.0 |
115
+ | 4.8296 | 6.75 | 4700 | 4.8388 | 1.0 |
116
+ | 4.828 | 6.9 | 4800 | 4.8374 | 1.0 |
117
+ | 4.8173 | 7.04 | 4900 | 4.8375 | 1.0 |
118
+ | 4.8234 | 7.18 | 5000 | 4.8348 | 1.0 |
119
+ | 4.8233 | 7.33 | 5100 | 4.8349 | 1.0 |
120
+ | 4.8232 | 7.47 | 5200 | 4.8339 | 1.0 |
121
+ | 4.8293 | 7.61 | 5300 | 4.8386 | 1.0 |
122
+ | 4.8305 | 7.76 | 5400 | 4.8385 | 1.0 |
123
+ | 4.8253 | 7.9 | 5500 | 4.8315 | 1.0 |
124
+ | 4.823 | 8.05 | 5600 | 4.8325 | 1.0 |
125
+ | 4.8313 | 8.19 | 5700 | 4.8311 | 1.0 |
126
+ | 4.8284 | 8.33 | 5800 | 4.8329 | 1.0 |
127
+ | 4.8199 | 8.48 | 5900 | 4.8329 | 1.0 |
128
+ | 4.8208 | 8.62 | 6000 | 4.8319 | 1.0 |
129
+ | 4.8315 | 8.76 | 6100 | 4.8334 | 1.0 |
130
+ | 4.8265 | 8.91 | 6200 | 4.8308 | 1.0 |
131
+ | 4.8218 | 9.05 | 6300 | 4.8313 | 1.0 |
132
+ | 4.8172 | 9.2 | 6400 | 4.8294 | 1.0 |
133
+ | 4.8231 | 9.34 | 6500 | 4.8299 | 1.0 |
134
+ | 4.825 | 9.48 | 6600 | 4.8311 | 1.0 |
135
+ | 4.826 | 9.63 | 6700 | 4.8299 | 1.0 |
136
+ | 4.8269 | 9.77 | 6800 | 4.8321 | 1.0 |
137
+ | 4.8275 | 9.91 | 6900 | 4.8306 | 1.0 |
138
+ | 4.8199 | 10.06 | 7000 | 4.8302 | 1.0 |
139
+ | 4.8217 | 10.2 | 7100 | 4.8316 | 1.0 |
140
+ | 4.8237 | 10.34 | 7200 | 4.8296 | 1.0 |
141
+ | 4.8253 | 10.49 | 7300 | 4.8318 | 1.0 |
142
+ | 4.8256 | 10.63 | 7400 | 4.8320 | 1.0 |
143
+ | 4.8265 | 10.78 | 7500 | 4.8297 | 1.0 |
144
+ | 4.8201 | 10.92 | 7600 | 4.8309 | 1.0 |
145
+ | 4.8259 | 11.06 | 7700 | 4.8302 | 1.0 |
146
+ | 4.8216 | 11.21 | 7800 | 4.8315 | 1.0 |
147
+ | 4.8206 | 11.35 | 7900 | 4.8328 | 1.0 |
148
+ | 4.8249 | 11.49 | 8000 | 4.8290 | 1.0 |
149
+ | 4.8231 | 11.64 | 8100 | 4.8297 | 1.0 |
150
+ | 4.8232 | 11.78 | 8200 | 4.8303 | 1.0 |
151
+ | 4.8245 | 11.93 | 8300 | 4.8283 | 1.0 |
152
+ | 4.8224 | 12.07 | 8400 | 4.8309 | 1.0 |
153
+ | 4.822 | 12.21 | 8500 | 4.8341 | 1.0 |
154
+ | 4.8234 | 12.36 | 8600 | 4.8300 | 1.0 |
155
+ | 4.8233 | 12.5 | 8700 | 4.8302 | 1.0 |
156
+ | 4.825 | 12.64 | 8800 | 4.8301 | 1.0 |
157
+ | 4.8246 | 12.79 | 8900 | 4.8310 | 1.0 |
158
+ | 4.8169 | 12.93 | 9000 | 4.8308 | 1.0 |
159
+ | 4.8194 | 13.07 | 9100 | 4.8319 | 1.0 |
160
+ | 4.8182 | 13.22 | 9200 | 4.8334 | 1.0 |
161
+ | 4.8245 | 13.36 | 9300 | 4.8334 | 1.0 |
162
+ | 4.8274 | 13.51 | 9400 | 4.8427 | 1.0 |
163
+ | 4.8194 | 13.65 | 9500 | 4.8393 | 1.0 |
164
+ | 4.825 | 13.79 | 9600 | 4.8368 | 1.0 |
165
+ | 4.8162 | 13.94 | 9700 | 4.8371 | 1.0 |
166
+ | 4.8213 | 14.08 | 9800 | 4.8359 | 1.0 |
167
+ | 4.8275 | 14.22 | 9900 | 4.8330 | 1.0 |
168
+ | 4.8119 | 14.37 | 10000 | 4.8328 | 1.0 |
169
+ | 4.8267 | 14.51 | 10100 | 4.8327 | 1.0 |
170
+ | 4.8218 | 14.66 | 10200 | 4.8328 | 1.0 |
171
+ | 4.8221 | 14.8 | 10300 | 4.8344 | 1.0 |
172
+ | 4.8181 | 14.94 | 10400 | 4.8330 | 1.0 |
173
+ | 4.8204 | 15.09 | 10500 | 4.8326 | 1.0 |
174
+ | 4.8235 | 15.23 | 10600 | 4.8340 | 1.0 |
175
+ | 4.8113 | 15.37 | 10700 | 4.8330 | 1.0 |
176
+ | 4.8268 | 15.52 | 10800 | 4.8330 | 1.0 |
177
+ | 4.8199 | 15.66 | 10900 | 4.8341 | 1.0 |
178
+ | 4.8213 | 15.8 | 11000 | 4.8320 | 1.0 |
179
+ | 4.8268 | 15.95 | 11100 | 4.8345 | 1.0 |
180
+ | 4.8113 | 16.09 | 11200 | 4.8367 | 1.0 |
181
+ | 4.8216 | 16.24 | 11300 | 4.8358 | 1.0 |
182
+ | 4.8287 | 16.38 | 11400 | 4.8343 | 1.0 |
183
+ | 4.8185 | 16.52 | 11500 | 4.8341 | 1.0 |
184
+ | 4.8226 | 16.67 | 11600 | 4.8321 | 1.0 |
185
+ | 4.8187 | 16.81 | 11700 | 4.8337 | 1.0 |
186
+ | 4.8183 | 16.95 | 11800 | 4.8324 | 1.0 |
187
+ | 4.8173 | 17.1 | 11900 | 4.8334 | 1.0 |
188
+ | 4.8217 | 17.24 | 12000 | 4.8338 | 1.0 |
189
+ | 4.8174 | 17.39 | 12100 | 4.8323 | 1.0 |
190
+ | 4.8193 | 17.53 | 12200 | 4.8358 | 1.0 |
191
+ | 4.8203 | 17.67 | 12300 | 4.8313 | 1.0 |
192
+ | 4.8182 | 17.82 | 12400 | 4.8311 | 1.0 |
193
+ | 4.8245 | 17.96 | 12500 | 4.8324 | 1.0 |
194
+ | 4.8195 | 18.1 | 12600 | 4.8301 | 1.0 |
195
+ | 4.8197 | 18.25 | 12700 | 4.8345 | 1.0 |
196
+ | 4.8163 | 18.39 | 12800 | 4.8326 | 1.0 |
197
+ | 4.8227 | 18.53 | 12900 | 4.8319 | 1.0 |
198
+ | 4.8254 | 18.68 | 13000 | 4.8321 | 1.0 |
199
+ | 4.8197 | 18.82 | 13100 | 4.8315 | 1.0 |
200
+ | 4.819 | 18.97 | 13200 | 4.8306 | 1.0 |
201
+ | 4.8106 | 19.11 | 13300 | 4.8297 | 1.0 |
202
+ | 4.8161 | 19.25 | 13400 | 4.8314 | 1.0 |
203
+ | 4.8147 | 19.4 | 13500 | 4.8340 | 1.0 |
204
+ | 4.8237 | 19.54 | 13600 | 4.8313 | 1.0 |
205
+ | 4.8186 | 19.68 | 13700 | 4.8298 | 1.0 |
206
+ | 4.8217 | 19.83 | 13800 | 4.8302 | 1.0 |
207
+ | 4.8239 | 19.97 | 13900 | 4.8297 | 1.0 |
208
+ | 4.8189 | 20.11 | 14000 | 4.8313 | 1.0 |
209
+ | 4.8254 | 20.26 | 14100 | 4.8299 | 1.0 |
210
+ | 4.8166 | 20.4 | 14200 | 4.8297 | 1.0 |
211
+ | 4.8199 | 20.55 | 14300 | 4.8294 | 1.0 |
212
+ | 4.8129 | 20.69 | 14400 | 4.8307 | 1.0 |
213
+ | 4.8175 | 20.83 | 14500 | 4.8285 | 1.0 |
214
+ | 4.8195 | 20.98 | 14600 | 4.8281 | 1.0 |
215
+ | 4.82 | 21.12 | 14700 | 4.8293 | 1.0 |
216
+ | 4.8136 | 21.26 | 14800 | 4.8293 | 1.0 |
217
+ | 4.8177 | 21.41 | 14900 | 4.8287 | 1.0 |
218
+ | 4.826 | 21.55 | 15000 | 4.8288 | 1.0 |
219
+ | 4.8177 | 21.7 | 15100 | 4.8296 | 1.0 |
220
+ | 4.8165 | 21.84 | 15200 | 4.8303 | 1.0 |
221
+ | 4.8246 | 21.98 | 15300 | 4.8282 | 1.0 |
222
+ | 4.8146 | 22.13 | 15400 | 4.8276 | 1.0 |
223
+ | 4.819 | 22.27 | 15500 | 4.8279 | 1.0 |
224
+ | 4.814 | 22.41 | 15600 | 4.8295 | 1.0 |
225
+ | 4.8195 | 22.56 | 15700 | 4.8274 | 1.0 |
226
+ | 4.8189 | 22.7 | 15800 | 4.8275 | 1.0 |
227
+ | 4.822 | 22.84 | 15900 | 4.8274 | 1.0 |
228
+ | 4.8195 | 22.99 | 16000 | 4.8274 | 1.0 |
229
+ | 4.8146 | 23.13 | 16100 | 4.8274 | 1.0 |
230
+ | 4.8126 | 23.28 | 16200 | 4.8271 | 1.0 |
231
+ | 4.8172 | 23.42 | 16300 | 4.8272 | 1.0 |
232
+ | 4.8214 | 23.56 | 16400 | 4.8277 | 1.0 |
233
+ | 4.821 | 23.71 | 16500 | 4.8278 | 1.0 |
234
+ | 4.8212 | 23.85 | 16600 | 4.8274 | 1.0 |
235
+ | 4.819 | 23.99 | 16700 | 4.8277 | 1.0 |
236
+ | 4.8165 | 24.14 | 16800 | 4.8274 | 1.0 |
237
+ | 4.8212 | 24.28 | 16900 | 4.8268 | 1.0 |
238
+ | 4.8198 | 24.43 | 17000 | 4.8272 | 1.0 |
239
+ | 4.8228 | 24.57 | 17100 | 4.8281 | 1.0 |
240
+ | 4.8159 | 24.71 | 17200 | 4.8272 | 1.0 |
241
+ | 4.8123 | 24.86 | 17300 | 4.8274 | 1.0 |
242
+ | 4.8143 | 25.0 | 17400 | 4.8284 | 1.0 |
243
+ | 4.8174 | 25.14 | 17500 | 4.8289 | 1.0 |
244
+ | 4.8243 | 25.29 | 17600 | 4.8276 | 1.0 |
245
+ | 4.8145 | 25.43 | 17700 | 4.8283 | 1.0 |
246
+ | 4.8129 | 25.57 | 17800 | 4.8277 | 1.0 |
247
+ | 4.815 | 25.72 | 17900 | 4.8272 | 1.0 |
248
+ | 4.8155 | 25.86 | 18000 | 4.8279 | 1.0 |
249
+ | 4.8217 | 26.01 | 18100 | 4.8269 | 1.0 |
250
+ | 4.8106 | 26.15 | 18200 | 4.8277 | 1.0 |
251
+ | 4.8188 | 26.29 | 18300 | 4.8270 | 1.0 |
252
+ | 4.8232 | 26.44 | 18400 | 4.8277 | 1.0 |
253
+ | 4.816 | 26.58 | 18500 | 4.8278 | 1.0 |
254
+ | 4.8159 | 26.72 | 18600 | 4.8275 | 1.0 |
255
+ | 4.8199 | 26.87 | 18700 | 4.8274 | 1.0 |
256
+ | 4.8149 | 27.01 | 18800 | 4.8278 | 1.0 |
257
+ | 4.8103 | 27.16 | 18900 | 4.8279 | 1.0 |
258
+ | 4.8244 | 27.3 | 19000 | 4.8275 | 1.0 |
259
+ | 4.8217 | 27.44 | 19100 | 4.8279 | 1.0 |
260
+ | 4.8168 | 27.59 | 19200 | 4.8277 | 1.0 |
261
+ | 4.8111 | 27.73 | 19300 | 4.8287 | 1.0 |
262
+ | 4.816 | 27.87 | 19400 | 4.8279 | 1.0 |
263
+ | 4.8166 | 28.02 | 19500 | 4.8282 | 1.0 |
264
+ | 4.8129 | 28.16 | 19600 | 4.8281 | 1.0 |
265
+ | 4.8207 | 28.3 | 19700 | 4.8275 | 1.0 |
266
+ | 4.8196 | 28.45 | 19800 | 4.8274 | 1.0 |
267
+ | 4.8208 | 28.59 | 19900 | 4.8277 | 1.0 |
268
+ | 4.811 | 28.74 | 20000 | 4.8280 | 1.0 |
269
+ | 4.8176 | 28.88 | 20100 | 4.8280 | 1.0 |
270
+ | 4.8126 | 29.02 | 20200 | 4.8283 | 1.0 |
271
+ | 4.8161 | 29.17 | 20300 | 4.8279 | 1.0 |
272
+ | 4.8134 | 29.31 | 20400 | 4.8278 | 1.0 |
273
+ | 4.8201 | 29.45 | 20500 | 4.8279 | 1.0 |
274
+ | 4.8185 | 29.6 | 20600 | 4.8283 | 1.0 |
275
+ | 4.8174 | 29.74 | 20700 | 4.8280 | 1.0 |
276
+ | 4.8145 | 29.89 | 20800 | 4.8280 | 1.0 |
277
+
278
+
279
+ ### Framework versions
280
+
281
+ - Transformers 4.24.0
282
+ - Pytorch 1.13.0+cu117
283
+ - Datasets 2.0.0
284
+ - Tokenizers 0.13.2