Hugging Face's logo

lgris
/
wav2vec2-xls-r-300m-gn-cv8

Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Guaraní
wav2vec2
Generated from Trainer
robust-speech-event
hf-asr-leaderboard
Eval Results
Inference Endpoints
Model card Files Metrics Community
lgris commited on
Commit
b21c3c6
•
1 Parent(s): abcbd9d

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +57 -57
README.md CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
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 common_voice dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 1.0820
20
- - Wer: 0.7212
21
 
22
  ## Model description
23
 
@@ -37,11 +37,11 @@ More information needed
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0001
40
- - train_batch_size: 1
41
  - eval_batch_size: 8
42
  - seed: 42
43
- - gradient_accumulation_steps: 8
44
- - total_train_batch_size: 8
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 100
@@ -52,61 +52,61 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:------:|:----:|:---------------:|:------:|
55
- | 12.7853 | 2.76 | 100 | 4.7861 | 1.0 |
56
- | 3.4153 | 5.55 | 200 | 3.5519 | 1.0 |
57
- | 3.2923 | 8.33 | 300 | 3.3052 | 1.0 |
58
- | 3.2119 | 11.11 | 400 | 3.1202 | 1.0 |
59
- | 2.5099 | 13.87 | 500 | 1.6023 | 0.9872 |
60
- | 1.3373 | 16.66 | 600 | 1.1878 | 0.9182 |
61
- | 0.913 | 19.44 | 700 | 1.0049 | 0.8875 |
62
- | 0.7013 | 22.22 | 800 | 0.9810 | 0.8542 |
63
- | 0.5439 | 24.98 | 900 | 0.9463 | 0.8568 |
64
- | 0.4581 | 27.76 | 1000 | 0.9771 | 0.8261 |
65
- | 0.392 | 30.55 | 1100 | 0.9489 | 0.8389 |
66
- | 0.3555 | 33.33 | 1200 | 0.8846 | 0.8107 |
67
- | 0.3219 | 36.11 | 1300 | 0.8567 | 0.7980 |
68
- | 0.2794 | 38.87 | 1400 | 0.8851 | 0.7775 |
69
- | 0.2649 | 41.66 | 1500 | 0.9642 | 0.7954 |
70
- | 0.2407 | 44.44 | 1600 | 0.9540 | 0.8133 |
71
- | 0.2184 | 47.22 | 1700 | 0.8820 | 0.7494 |
72
- | 0.2181 | 49.98 | 1800 | 0.9349 | 0.8031 |
73
- | 0.1863 | 52.76 | 1900 | 0.9557 | 0.7494 |
74
- | 0.1728 | 55.55 | 2000 | 1.0587 | 0.7519 |
75
- | 0.1848 | 58.33 | 2100 | 1.0072 | 0.8056 |
76
- | 0.1602 | 61.11 | 2200 | 0.9321 | 0.7980 |
77
- | 0.1479 | 63.87 | 2300 | 0.9669 | 0.8005 |
78
- | 0.1464 | 66.66 | 2400 | 0.9914 | 0.7545 |
79
- | 0.1442 | 69.44 | 2500 | 1.0479 | 0.8184 |
80
- | 0.1385 | 72.22 | 2600 | 1.0065 | 0.7647 |
81
- | 0.1201 | 74.98 | 2700 | 0.9956 | 0.7801 |
82
- | 0.1264 | 77.76 | 2800 | 1.0153 | 0.7801 |
83
- | 0.1143 | 80.55 | 2900 | 0.9973 | 0.7826 |
84
- | 0.1145 | 83.33 | 3000 | 0.9762 | 0.7698 |
85
- | 0.1264 | 86.11 | 3100 | 0.9494 | 0.7391 |
86
- | 0.1093 | 88.87 | 3200 | 1.0091 | 0.7801 |
87
- | 0.0988 | 91.66 | 3300 | 1.0605 | 0.7621 |
88
- | 0.103 | 94.44 | 3400 | 0.9910 | 0.7340 |
89
- | 0.0972 | 97.22 | 3500 | 1.0412 | 0.7519 |
90
- | 0.0974 | 99.98 | 3600 | 1.0361 | 0.7621 |
91
- | 0.0836 | 102.76 | 3700 | 0.9969 | 0.7673 |
92
- | 0.0795 | 105.55 | 3800 | 1.0198 | 0.7545 |
93
- | 0.0839 | 108.33 | 3900 | 1.0269 | 0.7698 |
94
- | 0.0856 | 111.11 | 4000 | 0.9913 | 0.7442 |
95
- | 0.0721 | 113.87 | 4100 | 1.0239 | 0.7621 |
96
- | 0.0711 | 116.66 | 4200 | 1.0360 | 0.7468 |
97
- | 0.0771 | 119.44 | 4300 | 1.0799 | 0.7289 |
98
- | 0.0624 | 122.22 | 4400 | 1.1323 | 0.7238 |
99
- | 0.0748 | 124.98 | 4500 | 1.0868 | 0.7366 |
100
- | 0.0644 | 127.76 | 4600 | 1.0658 | 0.7289 |
101
- | 0.0667 | 130.55 | 4700 | 1.0731 | 0.7212 |
102
- | 0.0624 | 133.33 | 4800 | 1.0794 | 0.7289 |
103
- | 0.0714 | 136.11 | 4900 | 1.0832 | 0.7238 |
104
- | 0.0627 | 138.87 | 5000 | 1.0820 | 0.7212 |
105
 
106
 
107
  ### Framework versions
108
 
109
- - Transformers 4.15.0
110
  - Pytorch 1.10.0+cu111
111
  - Datasets 1.18.1
112
- - Tokenizers 0.10.3
 
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 common_voice dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.9392
20
+ - Wer: 0.7033
21
 
22
  ## Model description
23
 
 
37
 
38
  The following hyperparameters were used during training:
39
  - learning_rate: 0.0001
40
+ - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
43
+ - gradient_accumulation_steps: 2
44
+ - total_train_batch_size: 16
45
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
  - lr_scheduler_type: linear
47
  - lr_scheduler_warmup_steps: 100
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss | Wer |
54
  |:-------------:|:------:|:----:|:---------------:|:------:|
55
+ | 20.0601 | 5.54 | 100 | 5.1622 | 1.0 |
56
+ | 3.7052 | 11.11 | 200 | 3.2869 | 1.0 |
57
+ | 3.3275 | 16.65 | 300 | 3.2162 | 1.0 |
58
+ | 3.2984 | 22.22 | 400 | 3.1638 | 1.0 |
59
+ | 3.1111 | 27.76 | 500 | 2.5541 | 1.0 |
60
+ | 2.238 | 33.32 | 600 | 1.2198 | 0.9616 |
61
+ | 1.5284 | 38.86 | 700 | 0.9571 | 0.8593 |
62
+ | 1.2735 | 44.43 | 800 | 0.8719 | 0.8363 |
63
+ | 1.1269 | 49.97 | 900 | 0.8334 | 0.7954 |
64
+ | 1.0427 | 55.54 | 1000 | 0.7700 | 0.7749 |
65
+ | 1.0152 | 61.11 | 1100 | 0.7747 | 0.7877 |
66
+ | 0.943 | 66.65 | 1200 | 0.7151 | 0.7442 |
67
+ | 0.9132 | 72.22 | 1300 | 0.7224 | 0.7289 |
68
+ | 0.8397 | 77.76 | 1400 | 0.7354 | 0.7059 |
69
+ | 0.8577 | 83.32 | 1500 | 0.7285 | 0.7263 |
70
+ | 0.7931 | 88.86 | 1600 | 0.7863 | 0.7084 |
71
+ | 0.7995 | 94.43 | 1700 | 0.7562 | 0.6880 |
72
+ | 0.799 | 99.97 | 1800 | 0.7905 | 0.7059 |
73
+ | 0.7373 | 105.54 | 1900 | 0.7791 | 0.7161 |
74
+ | 0.749 | 111.11 | 2000 | 0.8125 | 0.7161 |
75
+ | 0.6925 | 116.65 | 2100 | 0.7722 | 0.6905 |
76
+ | 0.7034 | 122.22 | 2200 | 0.8989 | 0.7136 |
77
+ | 0.6745 | 127.76 | 2300 | 0.8270 | 0.6982 |
78
+ | 0.6837 | 133.32 | 2400 | 0.8569 | 0.7161 |
79
+ | 0.6689 | 138.86 | 2500 | 0.8339 | 0.6982 |
80
+ | 0.6471 | 144.43 | 2600 | 0.8441 | 0.7110 |
81
+ | 0.615 | 149.97 | 2700 | 0.9038 | 0.7212 |
82
+ | 0.6477 | 155.54 | 2800 | 0.9089 | 0.7059 |
83
+ | 0.6047 | 161.11 | 2900 | 0.9149 | 0.7059 |
84
+ | 0.5613 | 166.65 | 3000 | 0.8582 | 0.7263 |
85
+ | 0.6017 | 172.22 | 3100 | 0.8787 | 0.7084 |
86
+ | 0.5546 | 177.76 | 3200 | 0.8753 | 0.6957 |
87
+ | 0.5747 | 183.32 | 3300 | 0.9167 | 0.7212 |
88
+ | 0.5535 | 188.86 | 3400 | 0.8448 | 0.6905 |
89
+ | 0.5331 | 194.43 | 3500 | 0.8644 | 0.7161 |
90
+ | 0.5428 | 199.97 | 3600 | 0.8730 | 0.7033 |
91
+ | 0.5219 | 205.54 | 3700 | 0.9047 | 0.6982 |
92
+ | 0.5158 | 211.11 | 3800 | 0.8706 | 0.7033 |
93
+ | 0.5107 | 216.65 | 3900 | 0.9139 | 0.7084 |
94
+ | 0.4903 | 222.22 | 4000 | 0.9456 | 0.7315 |
95
+ | 0.4772 | 227.76 | 4100 | 0.9475 | 0.7161 |
96
+ | 0.4713 | 233.32 | 4200 | 0.9237 | 0.7059 |
97
+ | 0.4743 | 238.86 | 4300 | 0.9305 | 0.6957 |
98
+ | 0.4705 | 244.43 | 4400 | 0.9561 | 0.7110 |
99
+ | 0.4908 | 249.97 | 4500 | 0.9389 | 0.7084 |
100
+ | 0.4717 | 255.54 | 4600 | 0.9234 | 0.6982 |
101
+ | 0.4462 | 261.11 | 4700 | 0.9323 | 0.6957 |
102
+ | 0.4556 | 266.65 | 4800 | 0.9432 | 0.7033 |
103
+ | 0.4691 | 272.22 | 4900 | 0.9389 | 0.7059 |
104
+ | 0.4601 | 277.76 | 5000 | 0.9392 | 0.7033 |
105
 
106
 
107
  ### Framework versions
108
 
109
+ - Transformers 4.16.0
110
  - Pytorch 1.10.0+cu111
111
  - Datasets 1.18.1
112
+ - Tokenizers 0.11.0