Hugging Face's logo

greenw0lf
/
wav2vec2-large-xls-r-2b-frisian-cv-8

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
greenw0lf commited on
Commit
92a452a
·
1 Parent(s): 8c53146

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +168 -0
README.md ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_8_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: wav2vec2-large-xls-r-2b-frisian-cv-8
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_8_0
17
+ type: common_voice_8_0
18
+ config: fy-NL
19
+ split: validation
20
+ args: fy-NL
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.040494215112126836
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # wav2vec2-large-xls-r-2b-frisian-cv-8
31
+
32
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-2b](https://huggingface.co/facebook/wav2vec2-xls-r-2b) on the common_voice_8_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.0465
35
+ - Wer: 0.0405
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
51
+ ### Training hyperparameters
52
+
53
+ The following hyperparameters were used during training:
54
+ - learning_rate: 3e-05
55
+ - train_batch_size: 16
56
+ - eval_batch_size: 8
57
+ - seed: 42
58
+ - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_ratio: 0.1
61
+ - num_epochs: 20
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
68
+ | 6.3316 | 0.21 | 400 | 2.9773 | 1.0 |
69
+ | 2.7465 | 0.43 | 800 | 1.2564 | 0.9352 |
70
+ | 1.4576 | 0.64 | 1200 | 0.6275 | 0.5809 |
71
+ | 1.2245 | 0.86 | 1600 | 0.4438 | 0.4244 |
72
+ | 0.9928 | 1.07 | 2000 | 0.3058 | 0.3247 |
73
+ | 0.8768 | 1.29 | 2400 | 0.2656 | 0.2618 |
74
+ | 0.8686 | 1.5 | 2800 | 0.2155 | 0.2289 |
75
+ | 0.8325 | 1.72 | 3200 | 0.1924 | 0.2016 |
76
+ | 0.8495 | 1.93 | 3600 | 0.1748 | 0.1853 |
77
+ | 0.7069 | 2.14 | 4000 | 0.1792 | 0.1682 |
78
+ | 0.7381 | 2.36 | 4400 | 0.1540 | 0.1524 |
79
+ | 0.6648 | 2.57 | 4800 | 0.1397 | 0.1477 |
80
+ | 0.7471 | 2.79 | 5200 | 0.1372 | 0.1389 |
81
+ | 0.7219 | 3.0 | 5600 | 0.1296 | 0.1308 |
82
+ | 0.5894 | 3.22 | 6000 | 0.1167 | 0.1287 |
83
+ | 0.585 | 3.43 | 6400 | 0.1194 | 0.1264 |
84
+ | 0.5486 | 3.65 | 6800 | 0.1159 | 0.1248 |
85
+ | 0.5001 | 3.86 | 7200 | 0.1107 | 0.1160 |
86
+ | 0.4838 | 4.08 | 7600 | 0.1079 | 0.1212 |
87
+ | 0.4213 | 4.29 | 8000 | 0.1065 | 0.1145 |
88
+ | 0.4493 | 4.5 | 8400 | 0.0998 | 0.1098 |
89
+ | 0.4003 | 4.72 | 8800 | 0.0975 | 0.1027 |
90
+ | 0.4034 | 4.93 | 9200 | 0.0947 | 0.1023 |
91
+ | 0.3699 | 5.15 | 9600 | 0.0927 | 0.1006 |
92
+ | 0.3748 | 5.36 | 10000 | 0.0955 | 0.0994 |
93
+ | 0.3681 | 5.58 | 10400 | 0.0923 | 0.0952 |
94
+ | 0.3416 | 5.79 | 10800 | 0.0902 | 0.0968 |
95
+ | 0.3594 | 6.01 | 11200 | 0.0848 | 0.0935 |
96
+ | 0.3303 | 6.22 | 11600 | 0.0889 | 0.0921 |
97
+ | 0.3205 | 6.43 | 12000 | 0.0843 | 0.0893 |
98
+ | 0.3267 | 6.65 | 12400 | 0.0884 | 0.0882 |
99
+ | 0.33 | 6.86 | 12800 | 0.0859 | 0.0936 |
100
+ | 0.3023 | 7.08 | 13200 | 0.0830 | 0.0851 |
101
+ | 0.3057 | 7.29 | 13600 | 0.0826 | 0.0860 |
102
+ | 0.3007 | 7.51 | 14000 | 0.0841 | 0.0836 |
103
+ | 0.2981 | 7.72 | 14400 | 0.0790 | 0.0817 |
104
+ | 0.282 | 7.94 | 14800 | 0.0761 | 0.0779 |
105
+ | 0.2758 | 8.15 | 15200 | 0.0767 | 0.0776 |
106
+ | 0.275 | 8.36 | 15600 | 0.0788 | 0.0781 |
107
+ | 0.283 | 8.58 | 16000 | 0.0728 | 0.0775 |
108
+ | 0.2684 | 8.79 | 16400 | 0.0722 | 0.0742 |
109
+ | 0.2701 | 9.01 | 16800 | 0.0742 | 0.0720 |
110
+ | 0.248 | 9.22 | 17200 | 0.0711 | 0.0729 |
111
+ | 0.2467 | 9.44 | 17600 | 0.0698 | 0.0711 |
112
+ | 0.2588 | 9.65 | 18000 | 0.0688 | 0.0710 |
113
+ | 0.2566 | 9.87 | 18400 | 0.0699 | 0.0708 |
114
+ | 0.2425 | 10.08 | 18800 | 0.0699 | 0.0683 |
115
+ | 0.2292 | 10.29 | 19200 | 0.0697 | 0.0662 |
116
+ | 0.2317 | 10.51 | 19600 | 0.0670 | 0.0663 |
117
+ | 0.2381 | 10.72 | 20000 | 0.0649 | 0.0648 |
118
+ | 0.2281 | 10.94 | 20400 | 0.0619 | 0.0621 |
119
+ | 0.2329 | 11.15 | 20800 | 0.0648 | 0.0627 |
120
+ | 0.2197 | 11.37 | 21200 | 0.0630 | 0.0632 |
121
+ | 0.2406 | 11.58 | 21600 | 0.0611 | 0.0609 |
122
+ | 0.2221 | 11.8 | 22000 | 0.0621 | 0.0601 |
123
+ | 0.2316 | 12.01 | 22400 | 0.0637 | 0.0596 |
124
+ | 0.202 | 12.23 | 22800 | 0.0622 | 0.0592 |
125
+ | 0.2071 | 12.44 | 23200 | 0.0603 | 0.0589 |
126
+ | 0.2119 | 12.65 | 23600 | 0.0589 | 0.0581 |
127
+ | 0.2072 | 12.87 | 24000 | 0.0586 | 0.0588 |
128
+ | 0.1948 | 13.08 | 24400 | 0.0576 | 0.0562 |
129
+ | 0.1967 | 13.3 | 24800 | 0.0573 | 0.0543 |
130
+ | 0.1981 | 13.51 | 25200 | 0.0582 | 0.0567 |
131
+ | 0.1869 | 13.73 | 25600 | 0.0550 | 0.0533 |
132
+ | 0.1929 | 13.94 | 26000 | 0.0530 | 0.0540 |
133
+ | 0.1837 | 14.16 | 26400 | 0.0550 | 0.0519 |
134
+ | 0.1823 | 14.37 | 26800 | 0.0535 | 0.0521 |
135
+ | 0.1756 | 14.58 | 27200 | 0.0552 | 0.0515 |
136
+ | 0.1769 | 14.8 | 27600 | 0.0553 | 0.0502 |
137
+ | 0.1769 | 15.01 | 28000 | 0.0516 | 0.0493 |
138
+ | 0.1781 | 15.23 | 28400 | 0.0519 | 0.0485 |
139
+ | 0.1763 | 15.44 | 28800 | 0.0511 | 0.0482 |
140
+ | 0.1705 | 15.66 | 29200 | 0.0513 | 0.0471 |
141
+ | 0.1696 | 15.87 | 29600 | 0.0484 | 0.0467 |
142
+ | 0.1668 | 16.09 | 30000 | 0.0492 | 0.0464 |
143
+ | 0.1635 | 16.3 | 30400 | 0.0492 | 0.0470 |
144
+ | 0.1597 | 16.51 | 30800 | 0.0505 | 0.0471 |
145
+ | 0.152 | 16.73 | 31200 | 0.0495 | 0.0471 |
146
+ | 0.1589 | 16.94 | 31600 | 0.0478 | 0.0456 |
147
+ | 0.1586 | 17.16 | 32000 | 0.0490 | 0.0441 |
148
+ | 0.1516 | 17.37 | 32400 | 0.0482 | 0.0448 |
149
+ | 0.1506 | 17.59 | 32800 | 0.0485 | 0.0439 |
150
+ | 0.1513 | 17.8 | 33200 | 0.0485 | 0.0439 |
151
+ | 0.1545 | 18.02 | 33600 | 0.0479 | 0.0432 |
152
+ | 0.1472 | 18.23 | 34000 | 0.0479 | 0.0428 |
153
+ | 0.148 | 18.45 | 34400 | 0.0475 | 0.0424 |
154
+ | 0.1446 | 18.66 | 34800 | 0.0477 | 0.0420 |
155
+ | 0.1413 | 18.87 | 35200 | 0.0466 | 0.0416 |
156
+ | 0.1398 | 19.09 | 35600 | 0.0477 | 0.0407 |
157
+ | 0.1431 | 19.3 | 36000 | 0.0466 | 0.0406 |
158
+ | 0.1437 | 19.52 | 36400 | 0.0467 | 0.0401 |
159
+ | 0.1393 | 19.73 | 36800 | 0.0468 | 0.0404 |
160
+ | 0.1416 | 19.95 | 37200 | 0.0465 | 0.0405 |
161
+
162
+
163
+ ### Framework versions
164
+
165
+ - Transformers 4.28.1
166
+ - Pytorch 2.0.0+cu117
167
+ - Datasets 2.11.0
168
+ - Tokenizers 0.13.3