hts98 commited on
Commit
3da2b7a
1 Parent(s): 342c491

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +109 -0
README.md ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ metrics:
6
+ - wer
7
+ model-index:
8
+ - name: wav2vec2-xls-r-300m-paper
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-xls-r-300m-paper
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.1744
20
+ - Wer: 0.3192
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 5e-05
40
+ - train_batch_size: 10
41
+ - eval_batch_size: 8
42
+ - seed: 42
43
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
+ - lr_scheduler_type: linear
45
+ - lr_scheduler_warmup_steps: 420
46
+ - num_epochs: 50.0
47
+
48
+ ### Training results
49
+
50
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
51
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
52
+ | No log | 1.0 | 335 | 3.7157 | 1.0 |
53
+ | 6.2976 | 2.0 | 670 | 3.3644 | 1.0 |
54
+ | 3.2342 | 3.0 | 1005 | 2.4597 | 0.9739 |
55
+ | 3.2342 | 4.0 | 1340 | 1.4160 | 0.7444 |
56
+ | 1.2813 | 5.0 | 1675 | 1.1338 | 0.6543 |
57
+ | 0.7279 | 6.0 | 2010 | 1.0020 | 0.5856 |
58
+ | 0.7279 | 7.0 | 2345 | 0.8435 | 0.4823 |
59
+ | 0.5226 | 8.0 | 2680 | 0.8757 | 0.5078 |
60
+ | 0.4218 | 9.0 | 3015 | 0.7895 | 0.4398 |
61
+ | 0.4218 | 10.0 | 3350 | 0.7992 | 0.4228 |
62
+ | 0.3421 | 11.0 | 3685 | 0.8118 | 0.4307 |
63
+ | 0.287 | 12.0 | 4020 | 0.8215 | 0.4248 |
64
+ | 0.287 | 13.0 | 4355 | 0.8603 | 0.4077 |
65
+ | 0.2415 | 14.0 | 4690 | 0.8329 | 0.3886 |
66
+ | 0.2132 | 15.0 | 5025 | 0.8728 | 0.3955 |
67
+ | 0.2132 | 16.0 | 5360 | 0.8741 | 0.3918 |
68
+ | 0.1857 | 17.0 | 5695 | 0.8633 | 0.3675 |
69
+ | 0.1673 | 18.0 | 6030 | 0.8884 | 0.3804 |
70
+ | 0.1673 | 19.0 | 6365 | 0.9141 | 0.3679 |
71
+ | 0.1479 | 20.0 | 6700 | 0.9568 | 0.3605 |
72
+ | 0.1386 | 21.0 | 7035 | 0.9341 | 0.3630 |
73
+ | 0.1386 | 22.0 | 7370 | 0.9645 | 0.3537 |
74
+ | 0.1233 | 23.0 | 7705 | 0.9729 | 0.3567 |
75
+ | 0.1177 | 24.0 | 8040 | 1.0013 | 0.3454 |
76
+ | 0.1177 | 25.0 | 8375 | 1.0323 | 0.3597 |
77
+ | 0.1061 | 26.0 | 8710 | 1.0269 | 0.3456 |
78
+ | 0.1028 | 27.0 | 9045 | 1.0042 | 0.3424 |
79
+ | 0.1028 | 28.0 | 9380 | 1.0424 | 0.3394 |
80
+ | 0.0961 | 29.0 | 9715 | 1.0600 | 0.3412 |
81
+ | 0.0949 | 30.0 | 10050 | 1.0512 | 0.3389 |
82
+ | 0.0949 | 31.0 | 10385 | 1.0957 | 0.3389 |
83
+ | 0.0878 | 32.0 | 10720 | 1.0924 | 0.3311 |
84
+ | 0.0852 | 33.0 | 11055 | 1.0859 | 0.3366 |
85
+ | 0.0852 | 34.0 | 11390 | 1.1498 | 0.3450 |
86
+ | 0.0837 | 35.0 | 11725 | 1.0844 | 0.3329 |
87
+ | 0.0814 | 36.0 | 12060 | 1.1051 | 0.3321 |
88
+ | 0.0814 | 37.0 | 12395 | 1.0878 | 0.3311 |
89
+ | 0.0793 | 38.0 | 12730 | 1.1377 | 0.3286 |
90
+ | 0.0759 | 39.0 | 13065 | 1.1136 | 0.3246 |
91
+ | 0.0759 | 40.0 | 13400 | 1.1216 | 0.3268 |
92
+ | 0.0726 | 41.0 | 13735 | 1.1300 | 0.3253 |
93
+ | 0.0715 | 42.0 | 14070 | 1.1507 | 0.3262 |
94
+ | 0.0715 | 43.0 | 14405 | 1.1562 | 0.3275 |
95
+ | 0.0711 | 44.0 | 14740 | 1.1486 | 0.3219 |
96
+ | 0.0699 | 45.0 | 15075 | 1.1580 | 0.3194 |
97
+ | 0.0699 | 46.0 | 15410 | 1.1580 | 0.3195 |
98
+ | 0.0667 | 47.0 | 15745 | 1.1504 | 0.3212 |
99
+ | 0.0667 | 48.0 | 16080 | 1.1580 | 0.3203 |
100
+ | 0.0667 | 49.0 | 16415 | 1.1698 | 0.3192 |
101
+ | 0.0664 | 50.0 | 16750 | 1.1744 | 0.3192 |
102
+
103
+
104
+ ### Framework versions
105
+
106
+ - Transformers 4.31.0.dev0
107
+ - Pytorch 2.0.0+cu117
108
+ - Datasets 2.7.0
109
+ - Tokenizers 0.13.2