Hugging Face's logo

hts98
/
wav2vec2-large-robust-paper

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
wav2vec2
hts98/original_ver1.2
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
hts98 commited on
Commit
406cd6c
•
1 Parent(s): acc5575

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-large-robust-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-large-robust-paper
16
+
17
+ This model is a fine-tuned version of [facebook/wav2vec2-large-robust](https://huggingface.co/facebook/wav2vec2-large-robust) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.3668
20
+ - Wer: 0.4372
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 | 3.9163 | 1.0 |
53
+ | 7.1369 | 2.0 | 670 | 3.3422 | 1.0 |
54
+ | 3.3448 | 3.0 | 1005 | 3.3355 | 1.0 |
55
+ | 3.3448 | 4.0 | 1340 | 3.3263 | 1.0 |
56
+ | 3.3277 | 5.0 | 1675 | 2.8928 | 1.0079 |
57
+ | 2.6655 | 6.0 | 2010 | 1.7822 | 0.8788 |
58
+ | 2.6655 | 7.0 | 2345 | 1.3193 | 0.7055 |
59
+ | 1.4617 | 8.0 | 2680 | 1.1408 | 0.6070 |
60
+ | 1.0805 | 9.0 | 3015 | 1.0108 | 0.5422 |
61
+ | 1.0805 | 10.0 | 3350 | 0.9517 | 0.5154 |
62
+ | 0.8759 | 11.0 | 3685 | 0.9082 | 0.4902 |
63
+ | 0.7462 | 12.0 | 4020 | 0.8758 | 0.4706 |
64
+ | 0.7462 | 13.0 | 4355 | 0.8696 | 0.4572 |
65
+ | 0.6429 | 14.0 | 4690 | 0.8731 | 0.4535 |
66
+ | 0.5672 | 15.0 | 5025 | 0.8749 | 0.4508 |
67
+ | 0.5672 | 16.0 | 5360 | 0.8753 | 0.4512 |
68
+ | 0.4959 | 17.0 | 5695 | 0.9039 | 0.4487 |
69
+ | 0.4456 | 18.0 | 6030 | 0.9161 | 0.4433 |
70
+ | 0.4456 | 19.0 | 6365 | 0.9506 | 0.4430 |
71
+ | 0.392 | 20.0 | 6700 | 0.9412 | 0.4439 |
72
+ | 0.3594 | 21.0 | 7035 | 0.9884 | 0.4416 |
73
+ | 0.3594 | 22.0 | 7370 | 1.0222 | 0.4510 |
74
+ | 0.3175 | 23.0 | 7705 | 1.0345 | 0.4439 |
75
+ | 0.2947 | 24.0 | 8040 | 1.0849 | 0.4465 |
76
+ | 0.2947 | 25.0 | 8375 | 1.0879 | 0.4472 |
77
+ | 0.2674 | 26.0 | 8710 | 1.1071 | 0.4512 |
78
+ | 0.2521 | 27.0 | 9045 | 1.1147 | 0.4494 |
79
+ | 0.2521 | 28.0 | 9380 | 1.1426 | 0.4525 |
80
+ | 0.2321 | 29.0 | 9715 | 1.1592 | 0.4440 |
81
+ | 0.2235 | 30.0 | 10050 | 1.1782 | 0.4450 |
82
+ | 0.2235 | 31.0 | 10385 | 1.2050 | 0.4437 |
83
+ | 0.2071 | 32.0 | 10720 | 1.2224 | 0.4400 |
84
+ | 0.1951 | 33.0 | 11055 | 1.2270 | 0.4471 |
85
+ | 0.1951 | 34.0 | 11390 | 1.2466 | 0.4483 |
86
+ | 0.1892 | 35.0 | 11725 | 1.2325 | 0.4429 |
87
+ | 0.1809 | 36.0 | 12060 | 1.2755 | 0.4427 |
88
+ | 0.1809 | 37.0 | 12395 | 1.2675 | 0.4422 |
89
+ | 0.1746 | 38.0 | 12730 | 1.3022 | 0.4418 |
90
+ | 0.1656 | 39.0 | 13065 | 1.3179 | 0.4408 |
91
+ | 0.1656 | 40.0 | 13400 | 1.2934 | 0.4425 |
92
+ | 0.1614 | 41.0 | 13735 | 1.3304 | 0.4426 |
93
+ | 0.1564 | 42.0 | 14070 | 1.3148 | 0.4420 |
94
+ | 0.1564 | 43.0 | 14405 | 1.3267 | 0.4433 |
95
+ | 0.1546 | 44.0 | 14740 | 1.3331 | 0.4413 |
96
+ | 0.1515 | 45.0 | 15075 | 1.3445 | 0.4388 |
97
+ | 0.1515 | 46.0 | 15410 | 1.3530 | 0.4372 |
98
+ | 0.147 | 47.0 | 15745 | 1.3443 | 0.4385 |
99
+ | 0.1447 | 48.0 | 16080 | 1.3503 | 0.4369 |
100
+ | 0.1447 | 49.0 | 16415 | 1.3590 | 0.4393 |
101
+ | 0.1437 | 50.0 | 16750 | 1.3668 | 0.4372 |
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