Hugging Face's logo

web2savar
/
w2v-fine-tune-test-no-ws2

Automatic Speech Recognition
Transformers
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Community
web2savar commited on
Commit
5a92b76
•
1 Parent(s): 3fbf334

End of training

Browse files
Files changed (2) hide show
  1. README.md +120 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,120 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: ylacombe/w2v-bert-2.0
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - common_voice_16_0
7
+ metrics:
8
+ - wer
9
+ model-index:
10
+ - name: w2v-fine-tune-test-no-ws2
11
+ results:
12
+ - task:
13
+ name: Automatic Speech Recognition
14
+ type: automatic-speech-recognition
15
+ dataset:
16
+ name: common_voice_16_0
17
+ type: common_voice_16_0
18
+ config: tr
19
+ split: test
20
+ args: tr
21
+ metrics:
22
+ - name: Wer
23
+ type: wer
24
+ value: 0.11088339984899148
25
+ ---
26
+
27
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
+ should probably proofread and complete it, then remove this comment. -->
29
+
30
+ # w2v-fine-tune-test-no-ws2
31
+
32
+ This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the common_voice_16_0 dataset.
33
+ It achieves the following results on the evaluation set:
34
+ - Loss: 0.1513
35
+ - Wer: 0.1109
36
+
37
+ ## Model description
38
+
39
+ More information needed
40
+
41
+ ## Intended uses & limitations
42
+
43
+ More information needed
44
+
45
+ ## Training and evaluation data
46
+
47
+ More information needed
48
+
49
+ ## Training procedure
50
+
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=(0.9,0.999) and epsilon=1e-08
59
+ - lr_scheduler_type: linear
60
+ - lr_scheduler_warmup_steps: 500
61
+ - num_epochs: 10
62
+ - mixed_precision_training: Native AMP
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
67
+ |:-------------:|:-----:|:-----:|:---------------:|:------:|
68
+ | 2.192 | 0.22 | 300 | 0.2797 | 0.2985 |
69
+ | 0.2226 | 0.44 | 600 | 0.2989 | 0.3491 |
70
+ | 0.1941 | 0.66 | 900 | 0.2558 | 0.2451 |
71
+ | 0.1659 | 0.88 | 1200 | 0.2320 | 0.2289 |
72
+ | 0.1332 | 1.1 | 1500 | 0.2063 | 0.1971 |
73
+ | 0.1129 | 1.31 | 1800 | 0.1873 | 0.2029 |
74
+ | 0.1044 | 1.53 | 2100 | 0.1765 | 0.1856 |
75
+ | 0.1026 | 1.75 | 2400 | 0.1719 | 0.1752 |
76
+ | 0.0982 | 1.97 | 2700 | 0.1927 | 0.2023 |
77
+ | 0.0769 | 2.19 | 3000 | 0.1776 | 0.1671 |
78
+ | 0.0715 | 2.41 | 3300 | 0.1626 | 0.1634 |
79
+ | 0.0695 | 2.63 | 3600 | 0.1666 | 0.1654 |
80
+ | 0.0612 | 2.85 | 3900 | 0.1760 | 0.1609 |
81
+ | 0.0614 | 3.07 | 4200 | 0.1645 | 0.1593 |
82
+ | 0.0476 | 3.29 | 4500 | 0.1685 | 0.1593 |
83
+ | 0.048 | 3.51 | 4800 | 0.1790 | 0.1583 |
84
+ | 0.0489 | 3.73 | 5100 | 0.1578 | 0.1535 |
85
+ | 0.0456 | 3.94 | 5400 | 0.1610 | 0.1617 |
86
+ | 0.041 | 4.16 | 5700 | 0.1559 | 0.1439 |
87
+ | 0.0367 | 4.38 | 6000 | 0.1536 | 0.1436 |
88
+ | 0.0321 | 4.6 | 6300 | 0.1591 | 0.1449 |
89
+ | 0.0349 | 4.82 | 6600 | 0.1616 | 0.1419 |
90
+ | 0.0308 | 5.04 | 6900 | 0.1501 | 0.1401 |
91
+ | 0.0233 | 5.26 | 7200 | 0.1588 | 0.1394 |
92
+ | 0.0253 | 5.48 | 7500 | 0.1633 | 0.1356 |
93
+ | 0.0254 | 5.7 | 7800 | 0.1522 | 0.1339 |
94
+ | 0.0245 | 5.92 | 8100 | 0.1598 | 0.1371 |
95
+ | 0.0189 | 6.14 | 8400 | 0.1497 | 0.1324 |
96
+ | 0.0174 | 6.36 | 8700 | 0.1487 | 0.1270 |
97
+ | 0.0178 | 6.57 | 9000 | 0.1397 | 0.1286 |
98
+ | 0.0173 | 6.79 | 9300 | 0.1495 | 0.1281 |
99
+ | 0.0178 | 7.01 | 9600 | 0.1462 | 0.1222 |
100
+ | 0.0124 | 7.23 | 9900 | 0.1516 | 0.1225 |
101
+ | 0.0121 | 7.45 | 10200 | 0.1554 | 0.1190 |
102
+ | 0.0128 | 7.67 | 10500 | 0.1453 | 0.1228 |
103
+ | 0.0113 | 7.89 | 10800 | 0.1468 | 0.1178 |
104
+ | 0.0086 | 8.11 | 11100 | 0.1556 | 0.1186 |
105
+ | 0.0085 | 8.33 | 11400 | 0.1507 | 0.1154 |
106
+ | 0.0073 | 8.55 | 11700 | 0.1494 | 0.1169 |
107
+ | 0.0079 | 8.77 | 12000 | 0.1507 | 0.1152 |
108
+ | 0.0089 | 8.98 | 12300 | 0.1456 | 0.1137 |
109
+ | 0.0062 | 9.2 | 12600 | 0.1518 | 0.1127 |
110
+ | 0.005 | 9.42 | 12900 | 0.1534 | 0.1115 |
111
+ | 0.005 | 9.64 | 13200 | 0.1514 | 0.1110 |
112
+ | 0.0048 | 9.86 | 13500 | 0.1513 | 0.1109 |
113
+
114
+
115
+ ### Framework versions
116
+
117
+ - Transformers 4.37.0.dev0
118
+ - Pytorch 2.1.2+cu121
119
+ - Datasets 2.16.1
120
+ - Tokenizers 0.15.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df319de64ec16eb976e23576b12f60dfc2c975e61af3e81f6ea5aca5be35ff69
3
  size 2422990860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d617e0d6fb4593e792db825b4644989ae7bab8555062bce062ebb83a36613749
3
  size 2422990860