Hugging Face's logo

alinerodrigues
/
wav2vec2-large-xlsr-coraa-exp-12

PyTorch
wav2vec2
Generated from Trainer
Model card Files Community
alinerodrigues commited on
Commit
e043ce8
·
1 Parent(s): 4c04d3f

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +189 -0
README.md ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: wav2vec2-large-xlsr-coraa-exp-12
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # wav2vec2-large-xlsr-coraa-exp-12
16
+
17
+ This model is a fine-tuned version of [Edresson/wav2vec2-large-xlsr-coraa-portuguese](https://huggingface.co/Edresson/wav2vec2-large-xlsr-coraa-portuguese) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.5762
20
+ - Wer: 0.3531
21
+ - Cer: 0.1822
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 3e-05
41
+ - train_batch_size: 16
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 32
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 150
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
55
+ | 37.6216 | 1.0 | 14 | 23.2071 | 1.0 | 0.9619 |
56
+ | 37.6216 | 2.0 | 28 | 6.9366 | 1.0 | 0.9619 |
57
+ | 37.6216 | 3.0 | 42 | 4.4250 | 1.0 | 0.9619 |
58
+ | 37.6216 | 4.0 | 56 | 3.9154 | 1.0 | 0.9619 |
59
+ | 37.6216 | 5.0 | 70 | 3.6849 | 1.0 | 0.9619 |
60
+ | 37.6216 | 6.0 | 84 | 3.5283 | 1.0 | 0.9619 |
61
+ | 37.6216 | 7.0 | 98 | 3.3716 | 1.0 | 0.9619 |
62
+ | 8.823 | 8.0 | 112 | 3.2657 | 1.0 | 0.9619 |
63
+ | 8.823 | 9.0 | 126 | 3.1796 | 1.0 | 0.9619 |
64
+ | 8.823 | 10.0 | 140 | 3.1568 | 1.0 | 0.9619 |
65
+ | 8.823 | 11.0 | 154 | 3.1071 | 1.0 | 0.9619 |
66
+ | 8.823 | 12.0 | 168 | 3.0891 | 1.0 | 0.9619 |
67
+ | 8.823 | 13.0 | 182 | 3.0588 | 1.0 | 0.9619 |
68
+ | 8.823 | 14.0 | 196 | 3.0422 | 1.0 | 0.9619 |
69
+ | 3.0574 | 15.0 | 210 | 3.0388 | 1.0 | 0.9619 |
70
+ | 3.0574 | 16.0 | 224 | 3.0324 | 1.0 | 0.9619 |
71
+ | 3.0574 | 17.0 | 238 | 3.0253 | 1.0 | 0.9619 |
72
+ | 3.0574 | 18.0 | 252 | 3.0100 | 1.0 | 0.9619 |
73
+ | 3.0574 | 19.0 | 266 | 3.0079 | 1.0 | 0.9619 |
74
+ | 3.0574 | 20.0 | 280 | 3.0150 | 1.0 | 0.9619 |
75
+ | 3.0574 | 21.0 | 294 | 3.0033 | 1.0 | 0.9619 |
76
+ | 2.95 | 22.0 | 308 | 2.9999 | 1.0 | 0.9619 |
77
+ | 2.95 | 23.0 | 322 | 2.9940 | 1.0 | 0.9619 |
78
+ | 2.95 | 24.0 | 336 | 2.9982 | 1.0 | 0.9619 |
79
+ | 2.95 | 25.0 | 350 | 3.0212 | 1.0 | 0.9619 |
80
+ | 2.95 | 26.0 | 364 | 2.9951 | 1.0 | 0.9619 |
81
+ | 2.95 | 27.0 | 378 | 2.9893 | 1.0 | 0.9619 |
82
+ | 2.95 | 28.0 | 392 | 2.9907 | 1.0 | 0.9619 |
83
+ | 2.9233 | 29.0 | 406 | 2.9889 | 1.0 | 0.9619 |
84
+ | 2.9233 | 30.0 | 420 | 2.9813 | 1.0 | 0.9619 |
85
+ | 2.9233 | 31.0 | 434 | 2.9795 | 1.0 | 0.9619 |
86
+ | 2.9233 | 32.0 | 448 | 2.9633 | 1.0 | 0.9619 |
87
+ | 2.9233 | 33.0 | 462 | 2.9653 | 1.0 | 0.9585 |
88
+ | 2.9233 | 34.0 | 476 | 2.9050 | 1.0 | 0.9619 |
89
+ | 2.9233 | 35.0 | 490 | 2.8806 | 1.0 | 0.9619 |
90
+ | 2.8852 | 36.0 | 504 | 2.8230 | 1.0 | 0.9619 |
91
+ | 2.8852 | 37.0 | 518 | 2.7805 | 1.0 | 0.9619 |
92
+ | 2.8852 | 38.0 | 532 | 2.7044 | 1.0 | 0.9572 |
93
+ | 2.8852 | 39.0 | 546 | 2.6561 | 1.0 | 0.9559 |
94
+ | 2.8852 | 40.0 | 560 | 2.5475 | 1.0 | 0.9254 |
95
+ | 2.8852 | 41.0 | 574 | 2.3336 | 1.0 | 0.7458 |
96
+ | 2.8852 | 42.0 | 588 | 2.0696 | 1.0 | 0.5468 |
97
+ | 2.5339 | 43.0 | 602 | 1.7760 | 1.0 | 0.4971 |
98
+ | 2.5339 | 44.0 | 616 | 1.5433 | 1.0 | 0.4546 |
99
+ | 2.5339 | 45.0 | 630 | 1.3529 | 1.0 | 0.4067 |
100
+ | 2.5339 | 46.0 | 644 | 1.2149 | 0.9998 | 0.3834 |
101
+ | 2.5339 | 47.0 | 658 | 1.0925 | 0.9943 | 0.3578 |
102
+ | 2.5339 | 48.0 | 672 | 1.0236 | 0.8954 | 0.3129 |
103
+ | 2.5339 | 49.0 | 686 | 0.9525 | 0.7062 | 0.2623 |
104
+ | 1.3395 | 50.0 | 700 | 0.8922 | 0.5063 | 0.2201 |
105
+ | 1.3395 | 51.0 | 714 | 0.8068 | 0.4774 | 0.2115 |
106
+ | 1.3395 | 52.0 | 728 | 0.7932 | 0.4553 | 0.2076 |
107
+ | 1.3395 | 53.0 | 742 | 0.7726 | 0.4453 | 0.2066 |
108
+ | 1.3395 | 54.0 | 756 | 0.7551 | 0.4340 | 0.2027 |
109
+ | 1.3395 | 55.0 | 770 | 0.7420 | 0.4305 | 0.2039 |
110
+ | 1.3395 | 56.0 | 784 | 0.7146 | 0.4212 | 0.2008 |
111
+ | 1.3395 | 57.0 | 798 | 0.6768 | 0.4096 | 0.1957 |
112
+ | 0.7419 | 58.0 | 812 | 0.6767 | 0.4080 | 0.1962 |
113
+ | 0.7419 | 59.0 | 826 | 0.6709 | 0.4069 | 0.1971 |
114
+ | 0.7419 | 60.0 | 840 | 0.6791 | 0.4025 | 0.1967 |
115
+ | 0.7419 | 61.0 | 854 | 0.6560 | 0.4029 | 0.1938 |
116
+ | 0.7419 | 62.0 | 868 | 0.6474 | 0.3976 | 0.1939 |
117
+ | 0.7419 | 63.0 | 882 | 0.6584 | 0.3982 | 0.1941 |
118
+ | 0.7419 | 64.0 | 896 | 0.6619 | 0.3960 | 0.1938 |
119
+ | 0.5254 | 65.0 | 910 | 0.6514 | 0.3923 | 0.1936 |
120
+ | 0.5254 | 66.0 | 924 | 0.6363 | 0.3874 | 0.1915 |
121
+ | 0.5254 | 67.0 | 938 | 0.6173 | 0.3797 | 0.1900 |
122
+ | 0.5254 | 68.0 | 952 | 0.6284 | 0.3887 | 0.1918 |
123
+ | 0.5254 | 69.0 | 966 | 0.6153 | 0.3767 | 0.1897 |
124
+ | 0.5254 | 70.0 | 980 | 0.6084 | 0.3736 | 0.1879 |
125
+ | 0.5254 | 71.0 | 994 | 0.6196 | 0.3773 | 0.1900 |
126
+ | 0.4219 | 72.0 | 1008 | 0.6075 | 0.3730 | 0.1899 |
127
+ | 0.4219 | 73.0 | 1022 | 0.6017 | 0.3712 | 0.1884 |
128
+ | 0.4219 | 74.0 | 1036 | 0.5947 | 0.3694 | 0.1872 |
129
+ | 0.4219 | 75.0 | 1050 | 0.5975 | 0.3696 | 0.1889 |
130
+ | 0.4219 | 76.0 | 1064 | 0.6020 | 0.3728 | 0.1887 |
131
+ | 0.4219 | 77.0 | 1078 | 0.5994 | 0.3704 | 0.1892 |
132
+ | 0.4219 | 78.0 | 1092 | 0.5822 | 0.3716 | 0.1877 |
133
+ | 0.385 | 79.0 | 1106 | 0.6073 | 0.3742 | 0.1893 |
134
+ | 0.385 | 80.0 | 1120 | 0.6029 | 0.3728 | 0.1874 |
135
+ | 0.385 | 81.0 | 1134 | 0.5961 | 0.3700 | 0.1868 |
136
+ | 0.385 | 82.0 | 1148 | 0.6032 | 0.3702 | 0.1870 |
137
+ | 0.385 | 83.0 | 1162 | 0.6115 | 0.3722 | 0.1889 |
138
+ | 0.385 | 84.0 | 1176 | 0.6018 | 0.3690 | 0.1883 |
139
+ | 0.385 | 85.0 | 1190 | 0.5824 | 0.3665 | 0.1855 |
140
+ | 0.3463 | 86.0 | 1204 | 0.5985 | 0.3669 | 0.1866 |
141
+ | 0.3463 | 87.0 | 1218 | 0.5833 | 0.3669 | 0.1861 |
142
+ | 0.3463 | 88.0 | 1232 | 0.5775 | 0.3637 | 0.1862 |
143
+ | 0.3463 | 89.0 | 1246 | 0.5747 | 0.3606 | 0.1850 |
144
+ | 0.3463 | 90.0 | 1260 | 0.5784 | 0.3639 | 0.1851 |
145
+ | 0.3463 | 91.0 | 1274 | 0.5841 | 0.3604 | 0.1858 |
146
+ | 0.3463 | 92.0 | 1288 | 0.5762 | 0.3655 | 0.1850 |
147
+ | 0.3237 | 93.0 | 1302 | 0.5836 | 0.3598 | 0.1854 |
148
+ | 0.3237 | 94.0 | 1316 | 0.5761 | 0.3588 | 0.1841 |
149
+ | 0.3237 | 95.0 | 1330 | 0.5822 | 0.3596 | 0.1848 |
150
+ | 0.3237 | 96.0 | 1344 | 0.5886 | 0.3592 | 0.1850 |
151
+ | 0.3237 | 97.0 | 1358 | 0.5696 | 0.3574 | 0.1830 |
152
+ | 0.3237 | 98.0 | 1372 | 0.5794 | 0.3588 | 0.1836 |
153
+ | 0.3237 | 99.0 | 1386 | 0.5768 | 0.3570 | 0.1837 |
154
+ | 0.2799 | 100.0 | 1400 | 0.5837 | 0.3578 | 0.1844 |
155
+ | 0.2799 | 101.0 | 1414 | 0.5697 | 0.3525 | 0.1826 |
156
+ | 0.2799 | 102.0 | 1428 | 0.5796 | 0.3566 | 0.1834 |
157
+ | 0.2799 | 103.0 | 1442 | 0.5712 | 0.3549 | 0.1825 |
158
+ | 0.2799 | 104.0 | 1456 | 0.5796 | 0.3555 | 0.1829 |
159
+ | 0.2799 | 105.0 | 1470 | 0.5759 | 0.3553 | 0.1835 |
160
+ | 0.2799 | 106.0 | 1484 | 0.5750 | 0.3562 | 0.1831 |
161
+ | 0.2799 | 107.0 | 1498 | 0.5650 | 0.3527 | 0.1823 |
162
+ | 0.2674 | 108.0 | 1512 | 0.5677 | 0.3499 | 0.1823 |
163
+ | 0.2674 | 109.0 | 1526 | 0.5699 | 0.3541 | 0.1826 |
164
+ | 0.2674 | 110.0 | 1540 | 0.5779 | 0.3555 | 0.1837 |
165
+ | 0.2674 | 111.0 | 1554 | 0.5792 | 0.3551 | 0.1834 |
166
+ | 0.2674 | 112.0 | 1568 | 0.5697 | 0.3574 | 0.1829 |
167
+ | 0.2674 | 113.0 | 1582 | 0.5852 | 0.3590 | 0.1839 |
168
+ | 0.2674 | 114.0 | 1596 | 0.5735 | 0.3537 | 0.1829 |
169
+ | 0.2611 | 115.0 | 1610 | 0.5774 | 0.3545 | 0.1832 |
170
+ | 0.2611 | 116.0 | 1624 | 0.5836 | 0.3555 | 0.1841 |
171
+ | 0.2611 | 117.0 | 1638 | 0.5750 | 0.3517 | 0.1832 |
172
+ | 0.2611 | 118.0 | 1652 | 0.5772 | 0.3521 | 0.1825 |
173
+ | 0.2611 | 119.0 | 1666 | 0.5793 | 0.3521 | 0.1831 |
174
+ | 0.2611 | 120.0 | 1680 | 0.5756 | 0.3517 | 0.1828 |
175
+ | 0.2611 | 121.0 | 1694 | 0.5794 | 0.3517 | 0.1830 |
176
+ | 0.2476 | 122.0 | 1708 | 0.5719 | 0.3521 | 0.1827 |
177
+ | 0.2476 | 123.0 | 1722 | 0.5804 | 0.3543 | 0.1830 |
178
+ | 0.2476 | 124.0 | 1736 | 0.5729 | 0.3539 | 0.1825 |
179
+ | 0.2476 | 125.0 | 1750 | 0.5874 | 0.3519 | 0.1832 |
180
+ | 0.2476 | 126.0 | 1764 | 0.5777 | 0.3533 | 0.1826 |
181
+ | 0.2476 | 127.0 | 1778 | 0.5762 | 0.3531 | 0.1822 |
182
+
183
+
184
+ ### Framework versions
185
+
186
+ - Transformers 4.28.0
187
+ - Pytorch 2.4.1+cu121
188
+ - Datasets 3.2.0
189
+ - Tokenizers 0.13.3