scarlett623
commited on
Commit
•
060b1c8
1
Parent(s):
4876ffb
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/wav2vec2-large-xlsr-53
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
datasets:
|
7 |
+
- common_voice
|
8 |
+
metrics:
|
9 |
+
- wer
|
10 |
+
model-index:
|
11 |
+
- name: wav2vec2-commonvoice-20subset-xlsr-53-gpu2
|
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: 0.9377853881278538
|
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-xlsr-53-gpu2
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the common_voice dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 1.7751
|
36 |
+
- Wer: 0.9378
|
37 |
+
- Cer: 0.2802
|
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 | 32.9239 | 1.0 | 1.0 |
|
72 |
+
| 69.7146 | 3.81 | 800 | 6.6878 | 1.0 | 1.0 |
|
73 |
+
| 7.0732 | 5.71 | 1200 | 6.4976 | 1.0 | 1.0 |
|
74 |
+
| 6.4558 | 7.62 | 1600 | 6.4214 | 1.0 | 1.0 |
|
75 |
+
| 6.2755 | 9.52 | 2000 | 6.2492 | 1.0143 | 0.9682 |
|
76 |
+
| 6.2755 | 11.43 | 2400 | 5.8545 | 1.0525 | 0.9396 |
|
77 |
+
| 5.8857 | 13.33 | 2800 | 4.4603 | 1.0742 | 0.7200 |
|
78 |
+
| 4.54 | 15.24 | 3200 | 3.7454 | 1.0297 | 0.6146 |
|
79 |
+
| 3.5614 | 17.14 | 3600 | 3.2387 | 1.0126 | 0.5582 |
|
80 |
+
| 2.9773 | 19.05 | 4000 | 2.8934 | 1.0068 | 0.5186 |
|
81 |
+
| 2.9773 | 20.95 | 4400 | 2.6116 | 0.9977 | 0.4880 |
|
82 |
+
| 2.5488 | 22.86 | 4800 | 2.4307 | 0.9932 | 0.4716 |
|
83 |
+
| 2.2665 | 24.76 | 5200 | 2.2844 | 0.9874 | 0.4532 |
|
84 |
+
| 2.0508 | 26.67 | 5600 | 2.1050 | 0.9886 | 0.4270 |
|
85 |
+
| 1.7944 | 28.57 | 6000 | 1.9768 | 0.9857 | 0.4150 |
|
86 |
+
| 1.7944 | 30.48 | 6400 | 1.8712 | 0.9789 | 0.3984 |
|
87 |
+
| 1.6074 | 32.38 | 6800 | 1.8050 | 0.9749 | 0.3916 |
|
88 |
+
| 1.4656 | 34.29 | 7200 | 1.7572 | 0.9783 | 0.3824 |
|
89 |
+
| 1.3429 | 36.19 | 7600 | 1.6546 | 0.9686 | 0.3677 |
|
90 |
+
| 1.2215 | 38.1 | 8000 | 1.6265 | 0.9726 | 0.3653 |
|
91 |
+
| 1.2215 | 40.0 | 8400 | 1.6046 | 0.9640 | 0.3625 |
|
92 |
+
| 1.1133 | 41.9 | 8800 | 1.5787 | 0.9737 | 0.3601 |
|
93 |
+
| 1.0702 | 43.81 | 9200 | 1.5449 | 0.9652 | 0.3503 |
|
94 |
+
| 0.9732 | 45.71 | 9600 | 1.5307 | 0.9572 | 0.3473 |
|
95 |
+
| 0.8858 | 47.62 | 10000 | 1.4962 | 0.9566 | 0.3394 |
|
96 |
+
| 0.8858 | 49.52 | 10400 | 1.5053 | 0.9561 | 0.3423 |
|
97 |
+
| 0.8067 | 51.43 | 10800 | 1.5053 | 0.9595 | 0.3389 |
|
98 |
+
| 0.7418 | 53.33 | 11200 | 1.4833 | 0.9566 | 0.3321 |
|
99 |
+
| 0.6962 | 55.24 | 11600 | 1.4927 | 0.9583 | 0.3312 |
|
100 |
+
| 0.6395 | 57.14 | 12000 | 1.4833 | 0.9509 | 0.3263 |
|
101 |
+
| 0.6395 | 59.05 | 12400 | 1.4908 | 0.9543 | 0.3263 |
|
102 |
+
| 0.5834 | 60.95 | 12800 | 1.4937 | 0.9521 | 0.3244 |
|
103 |
+
| 0.5422 | 62.86 | 13200 | 1.5123 | 0.9498 | 0.3206 |
|
104 |
+
| 0.4907 | 64.76 | 13600 | 1.5149 | 0.9515 | 0.3216 |
|
105 |
+
| 0.4525 | 66.67 | 14000 | 1.5079 | 0.9475 | 0.3206 |
|
106 |
+
| 0.4525 | 68.57 | 14400 | 1.5305 | 0.9469 | 0.3167 |
|
107 |
+
| 0.4229 | 70.48 | 14800 | 1.5427 | 0.9532 | 0.3235 |
|
108 |
+
| 0.3835 | 72.38 | 15200 | 1.5402 | 0.9452 | 0.3143 |
|
109 |
+
| 0.3642 | 74.29 | 15600 | 1.5569 | 0.9475 | 0.3151 |
|
110 |
+
| 0.3378 | 76.19 | 16000 | 1.5744 | 0.9463 | 0.3169 |
|
111 |
+
| 0.3378 | 78.1 | 16400 | 1.5578 | 0.9503 | 0.3122 |
|
112 |
+
| 0.3238 | 80.0 | 16800 | 1.5748 | 0.9481 | 0.3116 |
|
113 |
+
| 0.2997 | 81.9 | 17200 | 1.5708 | 0.9509 | 0.3139 |
|
114 |
+
| 0.2841 | 83.81 | 17600 | 1.5944 | 0.9521 | 0.3128 |
|
115 |
+
| 0.2573 | 85.71 | 18000 | 1.5941 | 0.9543 | 0.3108 |
|
116 |
+
| 0.2573 | 87.62 | 18400 | 1.6095 | 0.9515 | 0.3095 |
|
117 |
+
| 0.2496 | 89.52 | 18800 | 1.6170 | 0.9475 | 0.3102 |
|
118 |
+
| 0.2342 | 91.43 | 19200 | 1.6399 | 0.9469 | 0.3130 |
|
119 |
+
| 0.2261 | 93.33 | 19600 | 1.6241 | 0.9475 | 0.3099 |
|
120 |
+
| 0.2062 | 95.24 | 20000 | 1.6309 | 0.9446 | 0.3098 |
|
121 |
+
| 0.2062 | 97.14 | 20400 | 1.6360 | 0.9521 | 0.3061 |
|
122 |
+
| 0.2009 | 99.05 | 20800 | 1.6280 | 0.9526 | 0.3081 |
|
123 |
+
| 0.1916 | 100.95 | 21200 | 1.6606 | 0.9452 | 0.3053 |
|
124 |
+
| 0.1841 | 102.86 | 21600 | 1.6677 | 0.9475 | 0.3030 |
|
125 |
+
| 0.1794 | 104.76 | 22000 | 1.6625 | 0.9475 | 0.3039 |
|
126 |
+
| 0.1794 | 106.67 | 22400 | 1.6524 | 0.9481 | 0.3061 |
|
127 |
+
| 0.1718 | 108.57 | 22800 | 1.6761 | 0.9469 | 0.3085 |
|
128 |
+
| 0.174 | 110.48 | 23200 | 1.6778 | 0.9543 | 0.3048 |
|
129 |
+
| 0.1586 | 112.38 | 23600 | 1.6784 | 0.9503 | 0.3024 |
|
130 |
+
| 0.1595 | 114.29 | 24000 | 1.6844 | 0.9543 | 0.3021 |
|
131 |
+
| 0.1595 | 116.19 | 24400 | 1.6888 | 0.9463 | 0.3035 |
|
132 |
+
| 0.1494 | 118.1 | 24800 | 1.6767 | 0.9498 | 0.2984 |
|
133 |
+
| 0.141 | 120.0 | 25200 | 1.6898 | 0.9441 | 0.3044 |
|
134 |
+
| 0.139 | 121.9 | 25600 | 1.6812 | 0.9463 | 0.2990 |
|
135 |
+
| 0.1361 | 123.81 | 26000 | 1.6965 | 0.9446 | 0.2997 |
|
136 |
+
| 0.1361 | 125.71 | 26400 | 1.7046 | 0.9435 | 0.3014 |
|
137 |
+
| 0.1285 | 127.62 | 26800 | 1.6941 | 0.9463 | 0.2988 |
|
138 |
+
| 0.1273 | 129.52 | 27200 | 1.6980 | 0.9492 | 0.3008 |
|
139 |
+
| 0.1215 | 131.43 | 27600 | 1.7161 | 0.9424 | 0.2988 |
|
140 |
+
| 0.1188 | 133.33 | 28000 | 1.7033 | 0.9424 | 0.2976 |
|
141 |
+
| 0.1188 | 135.24 | 28400 | 1.7159 | 0.9446 | 0.2966 |
|
142 |
+
| 0.1183 | 137.14 | 28800 | 1.7157 | 0.9424 | 0.2965 |
|
143 |
+
| 0.118 | 139.05 | 29200 | 1.7073 | 0.9429 | 0.2932 |
|
144 |
+
| 0.1081 | 140.95 | 29600 | 1.7453 | 0.9424 | 0.2979 |
|
145 |
+
| 0.1064 | 142.86 | 30000 | 1.7120 | 0.9441 | 0.2964 |
|
146 |
+
| 0.1064 | 144.76 | 30400 | 1.7219 | 0.9418 | 0.2970 |
|
147 |
+
| 0.1028 | 146.67 | 30800 | 1.7217 | 0.9458 | 0.2960 |
|
148 |
+
| 0.1008 | 148.57 | 31200 | 1.7296 | 0.9481 | 0.2965 |
|
149 |
+
| 0.101 | 150.48 | 31600 | 1.7179 | 0.9412 | 0.2939 |
|
150 |
+
| 0.096 | 152.38 | 32000 | 1.7267 | 0.9418 | 0.2928 |
|
151 |
+
| 0.096 | 154.29 | 32400 | 1.7336 | 0.9401 | 0.2938 |
|
152 |
+
| 0.0898 | 156.19 | 32800 | 1.7229 | 0.9338 | 0.2921 |
|
153 |
+
| 0.0934 | 158.1 | 33200 | 1.7236 | 0.9406 | 0.2907 |
|
154 |
+
| 0.09 | 160.0 | 33600 | 1.7300 | 0.9378 | 0.2954 |
|
155 |
+
| 0.09 | 161.9 | 34000 | 1.7358 | 0.9435 | 0.2927 |
|
156 |
+
| 0.09 | 163.81 | 34400 | 1.7349 | 0.9452 | 0.2948 |
|
157 |
+
| 0.0886 | 165.71 | 34800 | 1.7336 | 0.9475 | 0.2935 |
|
158 |
+
| 0.0854 | 167.62 | 35200 | 1.7307 | 0.9429 | 0.2906 |
|
159 |
+
| 0.0829 | 169.52 | 35600 | 1.7329 | 0.9446 | 0.2947 |
|
160 |
+
| 0.0868 | 171.43 | 36000 | 1.7490 | 0.9446 | 0.2905 |
|
161 |
+
| 0.0868 | 173.33 | 36400 | 1.7322 | 0.9418 | 0.2929 |
|
162 |
+
| 0.0832 | 175.24 | 36800 | 1.7477 | 0.9441 | 0.2924 |
|
163 |
+
| 0.0792 | 177.14 | 37200 | 1.7541 | 0.9418 | 0.2897 |
|
164 |
+
| 0.0774 | 179.05 | 37600 | 1.7504 | 0.9424 | 0.2908 |
|
165 |
+
| 0.0754 | 180.95 | 38000 | 1.7516 | 0.9458 | 0.2925 |
|
166 |
+
| 0.0754 | 182.86 | 38400 | 1.7633 | 0.9469 | 0.2912 |
|
167 |
+
| 0.0779 | 184.76 | 38800 | 1.7526 | 0.9429 | 0.2928 |
|
168 |
+
| 0.0733 | 186.67 | 39200 | 1.7387 | 0.9412 | 0.2916 |
|
169 |
+
| 0.0765 | 188.57 | 39600 | 1.7464 | 0.9412 | 0.2900 |
|
170 |
+
| 0.0725 | 190.48 | 40000 | 1.7581 | 0.9384 | 0.2887 |
|
171 |
+
| 0.0725 | 192.38 | 40400 | 1.7424 | 0.9429 | 0.2872 |
|
172 |
+
| 0.0701 | 194.29 | 40800 | 1.7372 | 0.9401 | 0.2887 |
|
173 |
+
| 0.0707 | 196.19 | 41200 | 1.7570 | 0.9424 | 0.2904 |
|
174 |
+
| 0.0679 | 198.1 | 41600 | 1.7523 | 0.9418 | 0.2896 |
|
175 |
+
| 0.0649 | 200.0 | 42000 | 1.7767 | 0.9389 | 0.2891 |
|
176 |
+
| 0.0649 | 201.9 | 42400 | 1.7509 | 0.9412 | 0.2875 |
|
177 |
+
| 0.0654 | 203.81 | 42800 | 1.7480 | 0.9446 | 0.2878 |
|
178 |
+
| 0.0652 | 205.71 | 43200 | 1.7489 | 0.9395 | 0.2866 |
|
179 |
+
| 0.0642 | 207.62 | 43600 | 1.7609 | 0.9446 | 0.2871 |
|
180 |
+
| 0.0665 | 209.52 | 44000 | 1.7644 | 0.9412 | 0.2887 |
|
181 |
+
| 0.0665 | 211.43 | 44400 | 1.7583 | 0.9366 | 0.2882 |
|
182 |
+
| 0.0591 | 213.33 | 44800 | 1.7510 | 0.9384 | 0.2869 |
|
183 |
+
| 0.0593 | 215.24 | 45200 | 1.7632 | 0.9406 | 0.2874 |
|
184 |
+
| 0.0654 | 217.14 | 45600 | 1.7562 | 0.9418 | 0.2864 |
|
185 |
+
| 0.0571 | 219.05 | 46000 | 1.7585 | 0.9389 | 0.2850 |
|
186 |
+
| 0.0571 | 220.95 | 46400 | 1.7542 | 0.9389 | 0.2853 |
|
187 |
+
| 0.0576 | 222.86 | 46800 | 1.7625 | 0.9395 | 0.2857 |
|
188 |
+
| 0.0564 | 224.76 | 47200 | 1.7652 | 0.9384 | 0.2857 |
|
189 |
+
| 0.0566 | 226.67 | 47600 | 1.7698 | 0.9395 | 0.2829 |
|
190 |
+
| 0.0539 | 228.57 | 48000 | 1.7684 | 0.9378 | 0.2845 |
|
191 |
+
| 0.0539 | 230.48 | 48400 | 1.7737 | 0.9395 | 0.2849 |
|
192 |
+
| 0.0539 | 232.38 | 48800 | 1.7549 | 0.9349 | 0.2832 |
|
193 |
+
| 0.0533 | 234.29 | 49200 | 1.7548 | 0.9401 | 0.2839 |
|
194 |
+
| 0.0534 | 236.19 | 49600 | 1.7661 | 0.9372 | 0.2841 |
|
195 |
+
| 0.0514 | 238.1 | 50000 | 1.7680 | 0.9361 | 0.2844 |
|
196 |
+
| 0.0514 | 240.0 | 50400 | 1.7620 | 0.9384 | 0.2854 |
|
197 |
+
| 0.0504 | 241.9 | 50800 | 1.7744 | 0.9384 | 0.2841 |
|
198 |
+
| 0.0522 | 243.81 | 51200 | 1.7774 | 0.9344 | 0.2838 |
|
199 |
+
| 0.0486 | 245.71 | 51600 | 1.7739 | 0.9384 | 0.2839 |
|
200 |
+
| 0.0497 | 247.62 | 52000 | 1.7732 | 0.9389 | 0.2840 |
|
201 |
+
| 0.0497 | 249.52 | 52400 | 1.7705 | 0.9401 | 0.2842 |
|
202 |
+
| 0.0489 | 251.43 | 52800 | 1.7707 | 0.9424 | 0.2841 |
|
203 |
+
| 0.0496 | 253.33 | 53200 | 1.7754 | 0.9412 | 0.2830 |
|
204 |
+
| 0.0478 | 255.24 | 53600 | 1.7684 | 0.9429 | 0.2830 |
|
205 |
+
| 0.0515 | 257.14 | 54000 | 1.7675 | 0.9418 | 0.2815 |
|
206 |
+
| 0.0515 | 259.05 | 54400 | 1.7745 | 0.9429 | 0.2819 |
|
207 |
+
| 0.0474 | 260.95 | 54800 | 1.7783 | 0.9378 | 0.2820 |
|
208 |
+
| 0.0476 | 262.86 | 55200 | 1.7744 | 0.9418 | 0.2813 |
|
209 |
+
| 0.0448 | 264.76 | 55600 | 1.7715 | 0.9406 | 0.2822 |
|
210 |
+
| 0.0462 | 266.67 | 56000 | 1.7708 | 0.9389 | 0.2822 |
|
211 |
+
| 0.0462 | 268.57 | 56400 | 1.7719 | 0.9395 | 0.2820 |
|
212 |
+
| 0.0443 | 270.48 | 56800 | 1.7777 | 0.9384 | 0.2816 |
|
213 |
+
| 0.0445 | 272.38 | 57200 | 1.7750 | 0.9372 | 0.2807 |
|
214 |
+
| 0.0425 | 274.29 | 57600 | 1.7819 | 0.9412 | 0.2820 |
|
215 |
+
| 0.0449 | 276.19 | 58000 | 1.7765 | 0.9406 | 0.2807 |
|
216 |
+
| 0.0449 | 278.1 | 58400 | 1.7783 | 0.9366 | 0.2803 |
|
217 |
+
| 0.0434 | 280.0 | 58800 | 1.7719 | 0.9424 | 0.2809 |
|
218 |
+
| 0.0447 | 281.9 | 59200 | 1.7700 | 0.9355 | 0.2802 |
|
219 |
+
| 0.0465 | 283.81 | 59600 | 1.7747 | 0.9395 | 0.2802 |
|
220 |
+
| 0.0447 | 285.71 | 60000 | 1.7764 | 0.9384 | 0.2811 |
|
221 |
+
| 0.0447 | 287.62 | 60400 | 1.7799 | 0.9378 | 0.2807 |
|
222 |
+
| 0.0432 | 289.52 | 60800 | 1.7800 | 0.9384 | 0.2809 |
|
223 |
+
| 0.0431 | 291.43 | 61200 | 1.7785 | 0.9389 | 0.2807 |
|
224 |
+
| 0.0422 | 293.33 | 61600 | 1.7792 | 0.9395 | 0.2811 |
|
225 |
+
| 0.0418 | 295.24 | 62000 | 1.7749 | 0.9384 | 0.2807 |
|
226 |
+
| 0.0418 | 297.14 | 62400 | 1.7738 | 0.9384 | 0.2805 |
|
227 |
+
| 0.0416 | 299.05 | 62800 | 1.7751 | 0.9378 | 0.2802 |
|
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
|