Hugging Face's logo

scarlett623
/
wav2vec2-commonvoice-20subset-xls-r-300m-gpu1

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
scarlett623 commited on
Commit
7fd2f33
•
1 Parent(s): c65e315

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +235 -0
README.md ADDED
@@ -0,0 +1,235 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ base_model: facebook/wav2vec2-xls-r-300m
4
+ tags:
5
+ - generated_from_trainer
6
+ datasets:
7
+ - common_voice
8
+ metrics:
9
+ - wer
10
+ model-index:
11
+ - name: wav2vec2-commonvoice-20subset-xls-r-300m-gpu1
12
+ results:
13
+ - task:
14
+ name: Automatic Speech Recognition
15
+ type: automatic-speech-recognition
16
+ dataset:
17
+ name: common_voice
18
+ type: common_voice
19
+ config: zh-CN
20
+ split: test[:20%]
21
+ args: zh-CN
22
+ metrics:
23
+ - name: Wer
24
+ type: wer
25
+ value: 0.9320776255707762
26
+ ---
27
+
28
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
29
+ should probably proofread and complete it, then remove this comment. -->
30
+
31
+ # wav2vec2-commonvoice-20subset-xls-r-300m-gpu1
32
+
33
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
34
+ It achieves the following results on the evaluation set:
35
+ - Loss: 1.6717
36
+ - Wer: 0.9321
37
+ - Cer: 0.2636
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 5e-05
57
+ - train_batch_size: 13
58
+ - eval_batch_size: 2
59
+ - seed: 42
60
+ - gradient_accumulation_steps: 2
61
+ - total_train_batch_size: 26
62
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
63
+ - lr_scheduler_type: linear
64
+ - lr_scheduler_warmup_steps: 500
65
+ - num_epochs: 300
66
+
67
+ ### Training results
68
+
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
70
+ |:-------------:|:------:|:-----:|:---------------:|:------:|:------:|
71
+ | No log | 1.9 | 400 | 44.1474 | 1.0 | 1.0 |
72
+ | 69.9134 | 3.81 | 800 | 6.6651 | 1.0 | 1.0 |
73
+ | 7.6107 | 5.71 | 1200 | 6.5059 | 1.0 | 1.0 |
74
+ | 6.4614 | 7.62 | 1600 | 6.4456 | 1.0 | 1.0 |
75
+ | 6.3268 | 9.52 | 2000 | 6.3535 | 1.0 | 1.0000 |
76
+ | 6.3268 | 11.43 | 2400 | 6.1350 | 1.0063 | 0.9689 |
77
+ | 6.0793 | 13.33 | 2800 | 5.1209 | 1.0325 | 0.8288 |
78
+ | 5.2214 | 15.24 | 3200 | 4.3109 | 1.0148 | 0.6910 |
79
+ | 4.1439 | 17.14 | 3600 | 3.8123 | 1.0280 | 0.6100 |
80
+ | 3.558 | 19.05 | 4000 | 3.4451 | 1.0091 | 0.5639 |
81
+ | 3.558 | 20.95 | 4400 | 3.0901 | 1.0091 | 0.5271 |
82
+ | 3.0826 | 22.86 | 4800 | 2.7863 | 1.0080 | 0.4950 |
83
+ | 2.6891 | 24.76 | 5200 | 2.5825 | 1.0 | 0.4749 |
84
+ | 2.3535 | 26.67 | 5600 | 2.3098 | 1.0029 | 0.4420 |
85
+ | 2.0582 | 28.57 | 6000 | 2.1619 | 0.9960 | 0.4246 |
86
+ | 2.0582 | 30.48 | 6400 | 2.0340 | 0.9960 | 0.4097 |
87
+ | 1.8555 | 32.38 | 6800 | 1.9168 | 0.9874 | 0.3966 |
88
+ | 1.6825 | 34.29 | 7200 | 1.8196 | 0.9806 | 0.3849 |
89
+ | 1.4992 | 36.19 | 7600 | 1.7298 | 0.9863 | 0.3751 |
90
+ | 1.3534 | 38.1 | 8000 | 1.6588 | 0.9897 | 0.3674 |
91
+ | 1.3534 | 40.0 | 8400 | 1.6227 | 0.9823 | 0.3629 |
92
+ | 1.2413 | 41.9 | 8800 | 1.5783 | 0.9914 | 0.3556 |
93
+ | 1.1372 | 43.81 | 9200 | 1.5328 | 0.9755 | 0.3453 |
94
+ | 1.029 | 45.71 | 9600 | 1.5342 | 0.9726 | 0.3448 |
95
+ | 0.9409 | 47.62 | 10000 | 1.4863 | 0.9760 | 0.3362 |
96
+ | 0.9409 | 49.52 | 10400 | 1.4664 | 0.9715 | 0.3313 |
97
+ | 0.8615 | 51.43 | 10800 | 1.4799 | 0.9669 | 0.3337 |
98
+ | 0.7901 | 53.33 | 11200 | 1.4427 | 0.9635 | 0.3200 |
99
+ | 0.7302 | 55.24 | 11600 | 1.4679 | 0.9561 | 0.3244 |
100
+ | 0.6738 | 57.14 | 12000 | 1.4386 | 0.9521 | 0.3163 |
101
+ | 0.6738 | 59.05 | 12400 | 1.4515 | 0.9492 | 0.3139 |
102
+ | 0.6116 | 60.95 | 12800 | 1.4543 | 0.9526 | 0.3132 |
103
+ | 0.5558 | 62.86 | 13200 | 1.4303 | 0.9635 | 0.3079 |
104
+ | 0.504 | 64.76 | 13600 | 1.4425 | 0.9503 | 0.3045 |
105
+ | 0.4573 | 66.67 | 14000 | 1.4330 | 0.9515 | 0.3039 |
106
+ | 0.4573 | 68.57 | 14400 | 1.4553 | 0.9521 | 0.3017 |
107
+ | 0.429 | 70.48 | 14800 | 1.4727 | 0.9492 | 0.3031 |
108
+ | 0.3906 | 72.38 | 15200 | 1.4562 | 0.9458 | 0.3001 |
109
+ | 0.3664 | 74.29 | 15600 | 1.4699 | 0.9469 | 0.3007 |
110
+ | 0.3331 | 76.19 | 16000 | 1.4874 | 0.9515 | 0.3019 |
111
+ | 0.3331 | 78.1 | 16400 | 1.4866 | 0.9395 | 0.2999 |
112
+ | 0.3189 | 80.0 | 16800 | 1.4830 | 0.9412 | 0.2990 |
113
+ | 0.2963 | 81.9 | 17200 | 1.5135 | 0.9486 | 0.2984 |
114
+ | 0.2839 | 83.81 | 17600 | 1.5121 | 0.9475 | 0.2953 |
115
+ | 0.2602 | 85.71 | 18000 | 1.5313 | 0.9401 | 0.2990 |
116
+ | 0.2602 | 87.62 | 18400 | 1.5082 | 0.9418 | 0.2902 |
117
+ | 0.2515 | 89.52 | 18800 | 1.5320 | 0.9458 | 0.2969 |
118
+ | 0.2371 | 91.43 | 19200 | 1.5632 | 0.9446 | 0.2974 |
119
+ | 0.2327 | 93.33 | 19600 | 1.5268 | 0.9441 | 0.2942 |
120
+ | 0.2097 | 95.24 | 20000 | 1.5531 | 0.9406 | 0.2986 |
121
+ | 0.2097 | 97.14 | 20400 | 1.5443 | 0.9412 | 0.2923 |
122
+ | 0.1975 | 99.05 | 20800 | 1.5483 | 0.9418 | 0.2918 |
123
+ | 0.1886 | 100.95 | 21200 | 1.5669 | 0.9401 | 0.2909 |
124
+ | 0.1831 | 102.86 | 21600 | 1.5583 | 0.9389 | 0.2897 |
125
+ | 0.1762 | 104.76 | 22000 | 1.5557 | 0.9441 | 0.2904 |
126
+ | 0.1762 | 106.67 | 22400 | 1.5734 | 0.9366 | 0.2877 |
127
+ | 0.1681 | 108.57 | 22800 | 1.5873 | 0.9418 | 0.2917 |
128
+ | 0.1681 | 110.48 | 23200 | 1.5834 | 0.9395 | 0.2898 |
129
+ | 0.1542 | 112.38 | 23600 | 1.5941 | 0.9395 | 0.2861 |
130
+ | 0.1532 | 114.29 | 24000 | 1.5816 | 0.9424 | 0.2862 |
131
+ | 0.1532 | 116.19 | 24400 | 1.5806 | 0.9384 | 0.2850 |
132
+ | 0.1471 | 118.1 | 24800 | 1.5898 | 0.9418 | 0.2859 |
133
+ | 0.138 | 120.0 | 25200 | 1.6176 | 0.9412 | 0.2895 |
134
+ | 0.1361 | 121.9 | 25600 | 1.5888 | 0.9395 | 0.2865 |
135
+ | 0.1328 | 123.81 | 26000 | 1.6248 | 0.9418 | 0.2855 |
136
+ | 0.1328 | 125.71 | 26400 | 1.5954 | 0.9424 | 0.2864 |
137
+ | 0.123 | 127.62 | 26800 | 1.6179 | 0.9389 | 0.2844 |
138
+ | 0.1213 | 129.52 | 27200 | 1.6266 | 0.9418 | 0.2847 |
139
+ | 0.115 | 131.43 | 27600 | 1.6193 | 0.9406 | 0.2815 |
140
+ | 0.1137 | 133.33 | 28000 | 1.6255 | 0.9481 | 0.2868 |
141
+ | 0.1137 | 135.24 | 28400 | 1.6178 | 0.9378 | 0.2818 |
142
+ | 0.1089 | 137.14 | 28800 | 1.6339 | 0.9401 | 0.2827 |
143
+ | 0.1107 | 139.05 | 29200 | 1.6422 | 0.9378 | 0.2837 |
144
+ | 0.101 | 140.95 | 29600 | 1.6294 | 0.9418 | 0.2815 |
145
+ | 0.1006 | 142.86 | 30000 | 1.6290 | 0.9395 | 0.2843 |
146
+ | 0.1006 | 144.76 | 30400 | 1.6260 | 0.9384 | 0.2816 |
147
+ | 0.0991 | 146.67 | 30800 | 1.6283 | 0.9395 | 0.2801 |
148
+ | 0.0988 | 148.57 | 31200 | 1.6348 | 0.9435 | 0.2818 |
149
+ | 0.1 | 150.48 | 31600 | 1.6505 | 0.9435 | 0.2784 |
150
+ | 0.0927 | 152.38 | 32000 | 1.6468 | 0.9441 | 0.2798 |
151
+ | 0.0927 | 154.29 | 32400 | 1.6486 | 0.9424 | 0.2769 |
152
+ | 0.0851 | 156.19 | 32800 | 1.6455 | 0.9452 | 0.2811 |
153
+ | 0.089 | 158.1 | 33200 | 1.6307 | 0.9378 | 0.2776 |
154
+ | 0.0863 | 160.0 | 33600 | 1.6386 | 0.9355 | 0.2792 |
155
+ | 0.0852 | 161.9 | 34000 | 1.6244 | 0.9361 | 0.2757 |
156
+ | 0.0852 | 163.81 | 34400 | 1.6420 | 0.9389 | 0.2762 |
157
+ | 0.0835 | 165.71 | 34800 | 1.6474 | 0.9395 | 0.2749 |
158
+ | 0.0802 | 167.62 | 35200 | 1.6536 | 0.9406 | 0.2782 |
159
+ | 0.0787 | 169.52 | 35600 | 1.6594 | 0.9452 | 0.2796 |
160
+ | 0.0798 | 171.43 | 36000 | 1.6528 | 0.9366 | 0.2757 |
161
+ | 0.0798 | 173.33 | 36400 | 1.6518 | 0.9389 | 0.2747 |
162
+ | 0.0731 | 175.24 | 36800 | 1.6534 | 0.9406 | 0.2764 |
163
+ | 0.0745 | 177.14 | 37200 | 1.6638 | 0.9429 | 0.2770 |
164
+ | 0.0714 | 179.05 | 37600 | 1.6393 | 0.9406 | 0.2754 |
165
+ | 0.0694 | 180.95 | 38000 | 1.6421 | 0.9406 | 0.2746 |
166
+ | 0.0694 | 182.86 | 38400 | 1.6625 | 0.9378 | 0.2755 |
167
+ | 0.0727 | 184.76 | 38800 | 1.6549 | 0.9389 | 0.2753 |
168
+ | 0.0673 | 186.67 | 39200 | 1.6575 | 0.9406 | 0.2756 |
169
+ | 0.0695 | 188.57 | 39600 | 1.6684 | 0.9389 | 0.2737 |
170
+ | 0.0664 | 190.48 | 40000 | 1.6717 | 0.9429 | 0.2757 |
171
+ | 0.0664 | 192.38 | 40400 | 1.6636 | 0.9406 | 0.2751 |
172
+ | 0.0643 | 194.29 | 40800 | 1.6702 | 0.9441 | 0.2732 |
173
+ | 0.0627 | 196.19 | 41200 | 1.6517 | 0.9338 | 0.2735 |
174
+ | 0.0617 | 198.1 | 41600 | 1.6519 | 0.9378 | 0.2711 |
175
+ | 0.059 | 200.0 | 42000 | 1.6579 | 0.9378 | 0.2732 |
176
+ | 0.059 | 201.9 | 42400 | 1.6542 | 0.9315 | 0.2701 |
177
+ | 0.0595 | 203.81 | 42800 | 1.6607 | 0.9361 | 0.2713 |
178
+ | 0.0602 | 205.71 | 43200 | 1.6488 | 0.9378 | 0.2717 |
179
+ | 0.0581 | 207.62 | 43600 | 1.6651 | 0.9384 | 0.2693 |
180
+ | 0.0573 | 209.52 | 44000 | 1.6697 | 0.9384 | 0.2715 |
181
+ | 0.0573 | 211.43 | 44400 | 1.6585 | 0.9384 | 0.2708 |
182
+ | 0.0523 | 213.33 | 44800 | 1.6599 | 0.9372 | 0.2723 |
183
+ | 0.0541 | 215.24 | 45200 | 1.6683 | 0.9384 | 0.2732 |
184
+ | 0.0607 | 217.14 | 45600 | 1.6696 | 0.9355 | 0.2718 |
185
+ | 0.0512 | 219.05 | 46000 | 1.6733 | 0.9384 | 0.2740 |
186
+ | 0.0512 | 220.95 | 46400 | 1.6803 | 0.9372 | 0.2709 |
187
+ | 0.0515 | 222.86 | 46800 | 1.6684 | 0.9366 | 0.2692 |
188
+ | 0.0507 | 224.76 | 47200 | 1.6695 | 0.9315 | 0.2710 |
189
+ | 0.0502 | 226.67 | 47600 | 1.6789 | 0.9372 | 0.2692 |
190
+ | 0.0496 | 228.57 | 48000 | 1.6619 | 0.9326 | 0.2705 |
191
+ | 0.0496 | 230.48 | 48400 | 1.6707 | 0.9355 | 0.2705 |
192
+ | 0.049 | 232.38 | 48800 | 1.6655 | 0.9361 | 0.2688 |
193
+ | 0.0482 | 234.29 | 49200 | 1.6643 | 0.9389 | 0.2706 |
194
+ | 0.047 | 236.19 | 49600 | 1.6750 | 0.9355 | 0.2706 |
195
+ | 0.0474 | 238.1 | 50000 | 1.6913 | 0.9395 | 0.2719 |
196
+ | 0.0474 | 240.0 | 50400 | 1.6857 | 0.9384 | 0.2702 |
197
+ | 0.0458 | 241.9 | 50800 | 1.6815 | 0.9349 | 0.2664 |
198
+ | 0.0456 | 243.81 | 51200 | 1.6596 | 0.9378 | 0.2672 |
199
+ | 0.0423 | 245.71 | 51600 | 1.6623 | 0.9315 | 0.2664 |
200
+ | 0.0436 | 247.62 | 52000 | 1.6647 | 0.9344 | 0.2680 |
201
+ | 0.0436 | 249.52 | 52400 | 1.6706 | 0.9326 | 0.2671 |
202
+ | 0.043 | 251.43 | 52800 | 1.6751 | 0.9321 | 0.2687 |
203
+ | 0.043 | 253.33 | 53200 | 1.6706 | 0.9292 | 0.2688 |
204
+ | 0.0424 | 255.24 | 53600 | 1.6663 | 0.9304 | 0.2686 |
205
+ | 0.0431 | 257.14 | 54000 | 1.6684 | 0.9321 | 0.2674 |
206
+ | 0.0431 | 259.05 | 54400 | 1.6758 | 0.9309 | 0.2679 |
207
+ | 0.0405 | 260.95 | 54800 | 1.6666 | 0.9298 | 0.2667 |
208
+ | 0.0413 | 262.86 | 55200 | 1.6773 | 0.9315 | 0.2661 |
209
+ | 0.0393 | 264.76 | 55600 | 1.6702 | 0.9287 | 0.2650 |
210
+ | 0.0408 | 266.67 | 56000 | 1.6664 | 0.9332 | 0.2658 |
211
+ | 0.0408 | 268.57 | 56400 | 1.6738 | 0.9326 | 0.2660 |
212
+ | 0.0381 | 270.48 | 56800 | 1.6668 | 0.9332 | 0.2651 |
213
+ | 0.0383 | 272.38 | 57200 | 1.6747 | 0.9338 | 0.2651 |
214
+ | 0.0367 | 274.29 | 57600 | 1.6667 | 0.9304 | 0.2639 |
215
+ | 0.0393 | 276.19 | 58000 | 1.6743 | 0.9321 | 0.2643 |
216
+ | 0.0393 | 278.1 | 58400 | 1.6712 | 0.9326 | 0.2644 |
217
+ | 0.0377 | 280.0 | 58800 | 1.6759 | 0.9321 | 0.2637 |
218
+ | 0.0379 | 281.9 | 59200 | 1.6714 | 0.9315 | 0.2635 |
219
+ | 0.0376 | 283.81 | 59600 | 1.6798 | 0.9326 | 0.2643 |
220
+ | 0.0374 | 285.71 | 60000 | 1.6803 | 0.9338 | 0.2638 |
221
+ | 0.0374 | 287.62 | 60400 | 1.6764 | 0.9332 | 0.2645 |
222
+ | 0.0372 | 289.52 | 60800 | 1.6796 | 0.9326 | 0.2634 |
223
+ | 0.0354 | 291.43 | 61200 | 1.6762 | 0.9309 | 0.2628 |
224
+ | 0.0365 | 293.33 | 61600 | 1.6761 | 0.9315 | 0.2627 |
225
+ | 0.0349 | 295.24 | 62000 | 1.6746 | 0.9321 | 0.2631 |
226
+ | 0.0349 | 297.14 | 62400 | 1.6716 | 0.9321 | 0.2636 |
227
+ | 0.0345 | 299.05 | 62800 | 1.6717 | 0.9321 | 0.2636 |
228
+
229
+
230
+ ### Framework versions
231
+
232
+ - Transformers 4.31.0
233
+ - Pytorch 1.13.1+cu117
234
+ - Datasets 2.13.1
235
+ - Tokenizers 0.13.3