Hugging Face's logo

lucio
/
xls-r-uyghur-cv8

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
Uyghur
wav2vec2
Generated from Trainer
hf-asr-leaderboard
mozilla-foundation/common_voice_8_0
robust-speech-event
Eval Results
Inference Endpoints
Model card Files Metrics Community
3
lucio commited on
Commit
89dcecc
•
1 Parent(s): ae323bb

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +44 -60
README.md CHANGED
@@ -6,38 +6,22 @@ tags:
6
  - automatic-speech-recognition
7
  - mozilla-foundation/common_voice_8_0
8
  - generated_from_trainer
9
- - robust-speech-event
10
- - ug
11
  datasets:
12
- - mozilla-foundation/common_voice_8_0
13
  model-index:
14
- - name: XLS-R-300M Uyghur CV8
15
- results:
16
- - task:
17
- name: Automatic Speech Recognition
18
- type: automatic-speech-recognition
19
- dataset:
20
- name: Common Voice 8
21
- type: mozilla-foundation/common_voice_8_0
22
- args: ug
23
- metrics:
24
- - name: Test WER
25
- type: wer
26
- value: 36.33
27
- - name: Test CER
28
- type: cer
29
- value: 6.75
30
  ---
31
 
32
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
33
  should probably proofread and complete it, then remove this comment. -->
34
 
35
- # XLS-R-300M Uyghur CV8
36
 
37
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - UG dataset.
38
  It achieves the following results on the evaluation set:
39
- - Loss: 0.2240
40
- - Wer: 0.3693
41
 
42
  ## Model description
43
 
@@ -56,7 +40,7 @@ More information needed
56
  ### Training hyperparameters
57
 
58
  The following hyperparameters were used during training:
59
- - learning_rate: 4e-05
60
  - train_batch_size: 8
61
  - eval_batch_size: 8
62
  - seed: 42
@@ -72,43 +56,43 @@ The following hyperparameters were used during training:
72
 
73
  | Training Loss | Epoch | Step | Validation Loss | Wer |
74
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
75
- | 4.1169 | 2.66 | 500 | 4.0146 | 1.0 |
76
- | 3.2512 | 5.32 | 1000 | 3.2342 | 1.0 |
77
- | 2.5435 | 7.97 | 1500 | 1.8155 | 1.0286 |
78
- | 1.5575 | 10.64 | 2000 | 0.6346 | 0.7058 |
79
- | 1.3979 | 13.3 | 2500 | 0.4885 | 0.6320 |
80
- | 1.2874 | 15.95 | 3000 | 0.4271 | 0.6088 |
81
- | 1.2383 | 18.61 | 3500 | 0.3889 | 0.5869 |
82
- | 1.2054 | 21.28 | 4000 | 0.3609 | 0.5793 |
83
- | 1.1866 | 23.93 | 4500 | 0.3450 | 0.5513 |
84
- | 1.1332 | 26.59 | 5000 | 0.3214 | 0.5379 |
85
- | 1.135 | 29.25 | 5500 | 0.3122 | 0.5384 |
86
- | 1.0992 | 31.91 | 6000 | 0.2948 | 0.5078 |
87
- | 1.0707 | 34.57 | 6500 | 0.2928 | 0.5128 |
88
- | 1.0754 | 37.23 | 7000 | 0.2857 | 0.5017 |
89
- | 1.0461 | 39.89 | 7500 | 0.2791 | 0.5099 |
90
- | 1.0328 | 42.55 | 8000 | 0.2729 | 0.5120 |
91
- | 1.0201 | 45.21 | 8500 | 0.2654 | 0.4720 |
92
- | 1.0035 | 47.87 | 9000 | 0.2623 | 0.4659 |
93
- | 1.0069 | 50.53 | 9500 | 0.2569 | 0.4593 |
94
- | 0.9998 | 53.19 | 10000 | 0.2519 | 0.4405 |
95
- | 0.9762 | 55.85 | 10500 | 0.2505 | 0.4588 |
96
- | 0.9755 | 58.51 | 11000 | 0.2479 | 0.4564 |
97
- | 0.9624 | 61.17 | 11500 | 0.2460 | 0.4298 |
98
- | 0.9494 | 63.83 | 12000 | 0.2402 | 0.4182 |
99
- | 0.948 | 66.49 | 12500 | 0.2412 | 0.4212 |
100
- | 0.9312 | 69.15 | 13000 | 0.2352 | 0.3970 |
101
- | 0.9172 | 71.81 | 13500 | 0.2357 | 0.3926 |
102
- | 0.9101 | 74.47 | 14000 | 0.2305 | 0.3905 |
103
- | 0.9177 | 77.13 | 14500 | 0.2307 | 0.3838 |
104
- | 0.9083 | 79.78 | 15000 | 0.2313 | 0.3800 |
105
- | 0.9068 | 82.45 | 15500 | 0.2275 | 0.3742 |
106
- | 0.9087 | 85.11 | 16000 | 0.2283 | 0.3747 |
107
- | 0.8838 | 87.76 | 16500 | 0.2286 | 0.3777 |
108
- | 0.8868 | 90.42 | 17000 | 0.2269 | 0.3722 |
109
- | 0.8895 | 93.08 | 17500 | 0.2246 | 0.3714 |
110
- | 0.8926 | 95.74 | 18000 | 0.2241 | 0.3705 |
111
- | 0.8856 | 98.4 | 18500 | 0.2242 | 0.3693 |
112
 
113
 
114
  ### Framework versions
 
6
  - automatic-speech-recognition
7
  - mozilla-foundation/common_voice_8_0
8
  - generated_from_trainer
 
 
9
  datasets:
10
+ - common_voice
11
  model-index:
12
+ - name: xls-r-uyghur-cv8
13
+ results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # xls-r-uyghur-cv8
20
 
21
  This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - UG dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.2036
24
+ - Wer: 0.2977
25
 
26
  ## Model description
27
 
 
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
+ - learning_rate: 0.0001
44
  - train_batch_size: 8
45
  - eval_batch_size: 8
46
  - seed: 42
 
56
 
57
  | Training Loss | Epoch | Step | Validation Loss | Wer |
58
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
59
+ | 3.2892 | 2.66 | 500 | 3.2415 | 1.0 |
60
+ | 2.9206 | 5.32 | 1000 | 2.4381 | 1.0056 |
61
+ | 1.4909 | 7.97 | 1500 | 0.5428 | 0.6705 |
62
+ | 1.3395 | 10.64 | 2000 | 0.4207 | 0.5995 |
63
+ | 1.2718 | 13.3 | 2500 | 0.3743 | 0.5648 |
64
+ | 1.1798 | 15.95 | 3000 | 0.3225 | 0.4927 |
65
+ | 1.1392 | 18.61 | 3500 | 0.3097 | 0.4627 |
66
+ | 1.1143 | 21.28 | 4000 | 0.2996 | 0.4505 |
67
+ | 1.0923 | 23.93 | 4500 | 0.2841 | 0.4229 |
68
+ | 1.0516 | 26.59 | 5000 | 0.2705 | 0.4113 |
69
+ | 1.051 | 29.25 | 5500 | 0.2622 | 0.4078 |
70
+ | 1.021 | 31.91 | 6000 | 0.2611 | 0.4009 |
71
+ | 0.9886 | 34.57 | 6500 | 0.2498 | 0.3921 |
72
+ | 0.984 | 37.23 | 7000 | 0.2521 | 0.3845 |
73
+ | 0.9631 | 39.89 | 7500 | 0.2413 | 0.3791 |
74
+ | 0.9353 | 42.55 | 8000 | 0.2391 | 0.3612 |
75
+ | 0.922 | 45.21 | 8500 | 0.2363 | 0.3571 |
76
+ | 0.9116 | 47.87 | 9000 | 0.2285 | 0.3668 |
77
+ | 0.8951 | 50.53 | 9500 | 0.2256 | 0.3729 |
78
+ | 0.8865 | 53.19 | 10000 | 0.2228 | 0.3663 |
79
+ | 0.8792 | 55.85 | 10500 | 0.2221 | 0.3656 |
80
+ | 0.8682 | 58.51 | 11000 | 0.2228 | 0.3323 |
81
+ | 0.8492 | 61.17 | 11500 | 0.2167 | 0.3446 |
82
+ | 0.8365 | 63.83 | 12000 | 0.2156 | 0.3321 |
83
+ | 0.8298 | 66.49 | 12500 | 0.2142 | 0.3400 |
84
+ | 0.808 | 69.15 | 13000 | 0.2079 | 0.3148 |
85
+ | 0.7999 | 71.81 | 13500 | 0.2117 | 0.3225 |
86
+ | 0.7871 | 74.47 | 14000 | 0.2088 | 0.3174 |
87
+ | 0.7858 | 77.13 | 14500 | 0.2060 | 0.3008 |
88
+ | 0.7764 | 79.78 | 15000 | 0.2128 | 0.3146 |
89
+ | 0.7684 | 82.45 | 15500 | 0.2086 | 0.3101 |
90
+ | 0.7717 | 85.11 | 16000 | 0.2048 | 0.3069 |
91
+ | 0.7435 | 87.76 | 16500 | 0.2027 | 0.3055 |
92
+ | 0.7378 | 90.42 | 17000 | 0.2059 | 0.2993 |
93
+ | 0.7406 | 93.08 | 17500 | 0.2040 | 0.2966 |
94
+ | 0.7361 | 95.74 | 18000 | 0.2056 | 0.3000 |
95
+ | 0.7379 | 98.4 | 18500 | 0.2031 | 0.2976 |
96
 
97
 
98
  ### Framework versions