Hugging Face's logo

greenw0lf
/
wav2vec2-large-xls-r-1b-frisian-cv-8

Automatic Speech Recognition
Transformers
PyTorch
wav2vec2
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
greenw0lf commited on
Commit
c9210db
•
1 Parent(s): 93e5fca

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +34 -38
README.md CHANGED
@@ -21,20 +21,7 @@ model-index:
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 0.15637051849735753
25
- - task:
26
- name: Automatic Speech Recognition
27
- type: automatic-speech-recognition
28
- dataset:
29
- name: common_voice_8_0
30
- type: common_voice_8_0
31
- config: fy-NL
32
- split: test
33
- args: fy-NL
34
- metrics:
35
- - name: Wer
36
- type: wer
37
- value: 0.15204509322156382
38
  ---
39
 
40
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -44,8 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
44
 
45
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice_8_0 dataset.
46
  It achieves the following results on the evaluation set:
47
- - Loss: 0.2219
48
- - Wer: 0.1564
49
 
50
  ## Model description
51
 
@@ -64,8 +51,8 @@ More information needed
64
  ### Training hyperparameters
65
 
66
  The following hyperparameters were used during training:
67
- - learning_rate: 7e-05
68
- - train_batch_size: 30
69
  - eval_batch_size: 8
70
  - seed: 42
71
  - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
@@ -78,26 +65,35 @@ The following hyperparameters were used during training:
78
 
79
  | Training Loss | Epoch | Step | Validation Loss | Wer |
80
  |:-------------:|:-----:|:----:|:---------------:|:------:|
81
- | 4.9356 | 2.42 | 300 | 3.0022 | 1.0 |
82
- | 1.7278 | 4.84 | 600 | 0.4414 | 0.4147 |
83
- | 0.9407 | 7.26 | 900 | 0.3058 | 0.2955 |
84
- | 0.943 | 9.68 | 1200 | 0.2678 | 0.2530 |
85
- | 0.7468 | 12.1 | 1500 | 0.2443 | 0.2237 |
86
- | 0.6009 | 14.52 | 1800 | 0.2381 | 0.2097 |
87
- | 0.6101 | 16.94 | 2100 | 0.2339 | 0.2003 |
88
- | 0.5646 | 19.35 | 2400 | 0.2357 | 0.2047 |
89
- | 0.5875 | 21.77 | 2700 | 0.2219 | 0.1914 |
90
- | 0.5245 | 24.19 | 3000 | 0.2525 | 0.1807 |
91
- | 0.5971 | 26.61 | 3300 | 0.2432 | 0.1784 |
92
- | 0.563 | 29.03 | 3600 | 0.2454 | 0.1753 |
93
- | 0.4441 | 31.45 | 3900 | 0.2237 | 0.1776 |
94
- | 0.5552 | 33.87 | 4200 | 0.2313 | 0.1629 |
95
- | 0.5568 | 36.29 | 4500 | 0.2318 | 0.1602 |
96
- | 0.4342 | 38.71 | 4800 | 0.2324 | 0.1556 |
97
- | 0.4723 | 41.13 | 5100 | 0.2296 | 0.1602 |
98
- | 0.3357 | 43.55 | 5400 | 0.2267 | 0.1575 |
99
- | 0.4588 | 45.97 | 5700 | 0.2243 | 0.1558 |
100
- | 0.4594 | 48.39 | 6000 | 0.2219 | 0.1564 |
 
 
 
 
 
 
 
 
 
101
 
102
 
103
  ### Framework versions
 
21
  metrics:
22
  - name: Wer
23
  type: wer
24
+ value: 0.14290815597771747
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
31
 
32
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the common_voice_8_0 dataset.
33
  It achieves the following results on the evaluation set:
34
+ - Loss: 0.2131
35
+ - Wer: 0.1429
36
 
37
  ## Model description
38
 
 
51
  ### Training hyperparameters
52
 
53
  The following hyperparameters were used during training:
54
+ - learning_rate: 5e-05
55
+ - train_batch_size: 32
56
  - eval_batch_size: 8
57
  - seed: 42
58
  - optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08
 
65
 
66
  | Training Loss | Epoch | Step | Validation Loss | Wer |
67
  |:-------------:|:-----:|:----:|:---------------:|:------:|
68
+ | 6.0565 | 1.72 | 200 | 3.1053 | 1.0 |
69
+ | 2.7675 | 3.45 | 400 | 1.1551 | 0.8611 |
70
+ | 1.3474 | 5.17 | 600 | 0.4770 | 0.4397 |
71
+ | 0.9617 | 6.9 | 800 | 0.3218 | 0.3343 |
72
+ | 0.9058 | 8.62 | 1000 | 0.2741 | 0.2768 |
73
+ | 0.9712 | 10.34 | 1200 | 0.2619 | 0.2505 |
74
+ | 0.6908 | 12.07 | 1400 | 0.2288 | 0.2243 |
75
+ | 0.745 | 13.79 | 1600 | 0.2288 | 0.2095 |
76
+ | 0.7742 | 15.52 | 1800 | 0.2289 | 0.1979 |
77
+ | 0.7231 | 17.24 | 2000 | 0.2198 | 0.1940 |
78
+ | 0.6475 | 18.97 | 2200 | 0.2180 | 0.1992 |
79
+ | 0.6421 | 20.69 | 2400 | 0.2133 | 0.1741 |
80
+ | 0.5925 | 22.41 | 2600 | 0.1998 | 0.1747 |
81
+ | 0.5608 | 24.14 | 2800 | 0.2212 | 0.1950 |
82
+ | 0.5315 | 25.86 | 3000 | 0.2187 | 0.1624 |
83
+ | 0.5362 | 27.59 | 3200 | 0.2057 | 0.1718 |
84
+ | 0.563 | 29.31 | 3400 | 0.2090 | 0.1613 |
85
+ | 0.4218 | 31.03 | 3600 | 0.2126 | 0.1531 |
86
+ | 0.3826 | 32.76 | 3800 | 0.2084 | 0.1538 |
87
+ | 0.356 | 34.48 | 4000 | 0.2115 | 0.1612 |
88
+ | 0.2966 | 36.21 | 4200 | 0.2093 | 0.1536 |
89
+ | 0.3377 | 37.93 | 4400 | 0.2061 | 0.1527 |
90
+ | 0.321 | 39.66 | 4600 | 0.2121 | 0.1463 |
91
+ | 0.2942 | 41.38 | 4800 | 0.2158 | 0.1441 |
92
+ | 0.2931 | 43.1 | 5000 | 0.2173 | 0.1446 |
93
+ | 0.2346 | 44.83 | 5200 | 0.2152 | 0.1436 |
94
+ | 0.2543 | 46.55 | 5400 | 0.2066 | 0.1445 |
95
+ | 0.2385 | 48.28 | 5600 | 0.2108 | 0.1432 |
96
+ | 0.2726 | 50.0 | 5800 | 0.2131 | 0.1429 |
97
 
98
 
99
  ### Framework versions