Hugging Face's logo

alinerodrigues
/
wav2vec2-xlsr-1b-mecita-portuguese-all-text-protecao_aos_pandas

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Model card Files Community
alinerodrigues commited on
Commit
d047de0
·
1 Parent(s): b788c35

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +112 -0
README.md ADDED
@@ -0,0 +1,112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: wav2vec2-xlsr-1b-mecita-portuguese-all-text-protecao_aos_pandas
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-xlsr-1b-mecita-portuguese-all-text-protecao_aos_pandas
16
+
17
+ This model is a fine-tuned version of [jonatasgrosman/wav2vec2-xls-r-1b-portuguese](https://huggingface.co/jonatasgrosman/wav2vec2-xls-r-1b-portuguese) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.1881
20
+ - Wer: 0.1139
21
+ - Cer: 0.0303
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: 100
49
+ - mixed_precision_training: Native AMP
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
54
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
55
+ | 13.7229 | 0.93 | 7 | 4.8592 | 1.0 | 0.9996 |
56
+ | 13.7229 | 2.0 | 15 | 3.0023 | 1.0 | 1.0 |
57
+ | 13.7229 | 2.93 | 22 | 2.9290 | 1.0 | 1.0 |
58
+ | 13.7229 | 4.0 | 30 | 2.9842 | 1.0 | 1.0 |
59
+ | 13.7229 | 4.93 | 37 | 2.8453 | 1.0 | 1.0 |
60
+ | 13.7229 | 6.0 | 45 | 2.8120 | 1.0 | 1.0 |
61
+ | 13.7229 | 6.93 | 52 | 2.8162 | 1.0 | 1.0 |
62
+ | 13.7229 | 8.0 | 60 | 2.7843 | 1.0 | 1.0 |
63
+ | 13.7229 | 8.93 | 67 | 2.7823 | 1.0 | 1.0 |
64
+ | 13.7229 | 10.0 | 75 | 2.7434 | 1.0 | 1.0 |
65
+ | 13.7229 | 10.93 | 82 | 2.6364 | 1.0 | 1.0 |
66
+ | 13.7229 | 12.0 | 90 | 2.3797 | 0.9876 | 0.9861 |
67
+ | 13.7229 | 12.93 | 97 | 1.9516 | 0.9950 | 0.9771 |
68
+ | 3.3197 | 14.0 | 105 | 1.5396 | 1.0 | 0.7474 |
69
+ | 3.3197 | 14.93 | 112 | 1.1038 | 0.9950 | 0.4273 |
70
+ | 3.3197 | 16.0 | 120 | 0.6536 | 0.6733 | 0.1691 |
71
+ | 3.3197 | 16.93 | 127 | 0.4087 | 0.3218 | 0.0729 |
72
+ | 3.3197 | 18.0 | 135 | 0.3119 | 0.2252 | 0.0561 |
73
+ | 3.3197 | 18.93 | 142 | 0.2720 | 0.1757 | 0.0479 |
74
+ | 3.3197 | 20.0 | 150 | 0.2405 | 0.1584 | 0.0413 |
75
+ | 3.3197 | 20.93 | 157 | 0.2365 | 0.1584 | 0.0409 |
76
+ | 3.3197 | 22.0 | 165 | 0.2281 | 0.1510 | 0.0397 |
77
+ | 3.3197 | 22.93 | 172 | 0.1989 | 0.1361 | 0.0360 |
78
+ | 3.3197 | 24.0 | 180 | 0.2051 | 0.1287 | 0.0360 |
79
+ | 3.3197 | 24.93 | 187 | 0.2265 | 0.1287 | 0.0356 |
80
+ | 3.3197 | 26.0 | 195 | 0.2203 | 0.1287 | 0.0377 |
81
+ | 0.5589 | 26.93 | 202 | 0.2181 | 0.1213 | 0.0340 |
82
+ | 0.5589 | 28.0 | 210 | 0.2006 | 0.1238 | 0.0336 |
83
+ | 0.5589 | 28.93 | 217 | 0.1860 | 0.1213 | 0.0332 |
84
+ | 0.5589 | 30.0 | 225 | 0.1772 | 0.1114 | 0.0303 |
85
+ | 0.5589 | 30.93 | 232 | 0.1914 | 0.1238 | 0.0323 |
86
+ | 0.5589 | 32.0 | 240 | 0.1997 | 0.1238 | 0.0323 |
87
+ | 0.5589 | 32.93 | 247 | 0.1947 | 0.1262 | 0.0340 |
88
+ | 0.5589 | 34.0 | 255 | 0.2056 | 0.1213 | 0.0327 |
89
+ | 0.5589 | 34.93 | 262 | 0.1985 | 0.1213 | 0.0332 |
90
+ | 0.5589 | 36.0 | 270 | 0.2016 | 0.1213 | 0.0327 |
91
+ | 0.5589 | 36.93 | 277 | 0.1941 | 0.1139 | 0.0311 |
92
+ | 0.5589 | 38.0 | 285 | 0.1824 | 0.1238 | 0.0319 |
93
+ | 0.5589 | 38.93 | 292 | 0.1822 | 0.1089 | 0.0295 |
94
+ | 0.1503 | 40.0 | 300 | 0.1969 | 0.1163 | 0.0311 |
95
+ | 0.1503 | 40.93 | 307 | 0.1996 | 0.1163 | 0.0295 |
96
+ | 0.1503 | 42.0 | 315 | 0.1880 | 0.1089 | 0.0295 |
97
+ | 0.1503 | 42.93 | 322 | 0.2017 | 0.1312 | 0.0344 |
98
+ | 0.1503 | 44.0 | 330 | 0.1914 | 0.1163 | 0.0327 |
99
+ | 0.1503 | 44.93 | 337 | 0.1935 | 0.1163 | 0.0332 |
100
+ | 0.1503 | 46.0 | 345 | 0.1967 | 0.1139 | 0.0319 |
101
+ | 0.1503 | 46.93 | 352 | 0.1913 | 0.1064 | 0.0299 |
102
+ | 0.1503 | 48.0 | 360 | 0.1994 | 0.1114 | 0.0303 |
103
+ | 0.1503 | 48.93 | 367 | 0.1883 | 0.1089 | 0.0291 |
104
+ | 0.1503 | 50.0 | 375 | 0.1881 | 0.1139 | 0.0303 |
105
+
106
+
107
+ ### Framework versions
108
+
109
+ - Transformers 4.28.0
110
+ - Pytorch 2.2.1+cu121
111
+ - Datasets 2.17.0
112
+ - Tokenizers 0.13.3