Hugging Face's logo

vrclc
/
W2V2-BERT-Malayalam

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Bajiyo commited on
Commit
2411222
•
1 Parent(s): c66bbf3

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
  3. runs/May22_10-29-23_kudsit-dgxserver/events.out.tfevents.1716354727.kudsit-dgxserver.3904209.0 +2 -2
README.md CHANGED
@@ -1,10 +1,10 @@
1
  ---
2
  license: mit
 
3
  tags:
4
  - generated_from_trainer
5
  metrics:
6
  - wer
7
- base_model: facebook/w2v-bert-2.0
8
  model-index:
9
  - name: w2v-bert-2.0-nonstudio_and_studioRecords
10
  results: []
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
17
 
18
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.1629
21
- - Wer: 0.1284
22
 
23
  ## Model description
24
 
@@ -53,27 +53,27 @@ The following hyperparameters were used during training:
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
56
- | 1.1293 | 0.46 | 600 | 0.3873 | 0.4777 |
57
- | 0.1724 | 0.92 | 1200 | 0.2435 | 0.3533 |
58
- | 0.1229 | 1.38 | 1800 | 0.2188 | 0.2971 |
59
- | 0.109 | 1.84 | 2400 | 0.2135 | 0.2647 |
60
- | 0.0895 | 2.3 | 3000 | 0.1911 | 0.2441 |
61
- | 0.0779 | 2.76 | 3600 | 0.1738 | 0.2389 |
62
- | 0.0682 | 3.22 | 4200 | 0.1876 | 0.2476 |
63
- | 0.0568 | 3.68 | 4800 | 0.1603 | 0.2140 |
64
- | 0.0527 | 4.14 | 5400 | 0.1697 | 0.1809 |
65
- | 0.0422 | 4.6 | 6000 | 0.1656 | 0.1876 |
66
- | 0.0393 | 5.06 | 6600 | 0.1600 | 0.1732 |
67
- | 0.0311 | 5.52 | 7200 | 0.1522 | 0.1585 |
68
- | 0.0291 | 5.98 | 7800 | 0.1483 | 0.1543 |
69
- | 0.0207 | 6.44 | 8400 | 0.1561 | 0.1483 |
70
- | 0.0208 | 6.9 | 9000 | 0.1502 | 0.1391 |
71
- | 0.0151 | 7.36 | 9600 | 0.1561 | 0.1408 |
72
- | 0.0138 | 7.82 | 10200 | 0.1491 | 0.1296 |
73
- | 0.0108 | 8.28 | 10800 | 0.1472 | 0.1257 |
74
- | 0.008 | 8.74 | 11400 | 0.1658 | 0.1252 |
75
- | 0.0065 | 9.2 | 12000 | 0.1665 | 0.1227 |
76
- | 0.0045 | 9.66 | 12600 | 0.1629 | 0.1284 |
77
 
78
 
79
  ### Framework versions
 
1
  ---
2
  license: mit
3
+ base_model: facebook/w2v-bert-2.0
4
  tags:
5
  - generated_from_trainer
6
  metrics:
7
  - wer
 
8
  model-index:
9
  - name: w2v-bert-2.0-nonstudio_and_studioRecords
10
  results: []
 
17
 
18
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on an unknown dataset.
19
  It achieves the following results on the evaluation set:
20
+ - Loss: 0.1771
21
+ - Wer: 0.1179
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
56
+ | 1.1594 | 0.46 | 600 | 0.3721 | 0.4705 |
57
+ | 0.1751 | 0.92 | 1200 | 0.2652 | 0.3615 |
58
+ | 0.1269 | 1.38 | 1800 | 0.2069 | 0.2824 |
59
+ | 0.1113 | 1.84 | 2400 | 0.1867 | 0.2535 |
60
+ | 0.0904 | 2.3 | 3000 | 0.1907 | 0.2555 |
61
+ | 0.0783 | 2.76 | 3600 | 0.1740 | 0.2421 |
62
+ | 0.0691 | 3.22 | 4200 | 0.1860 | 0.2366 |
63
+ | 0.0588 | 3.68 | 4800 | 0.1696 | 0.2195 |
64
+ | 0.0541 | 4.14 | 5400 | 0.1560 | 0.1859 |
65
+ | 0.0421 | 4.6 | 6000 | 0.1812 | 0.1757 |
66
+ | 0.0385 | 5.06 | 6600 | 0.1643 | 0.1677 |
67
+ | 0.0305 | 5.52 | 7200 | 0.1457 | 0.1553 |
68
+ | 0.0309 | 5.98 | 7800 | 0.1494 | 0.1558 |
69
+ | 0.0214 | 6.44 | 8400 | 0.1516 | 0.1428 |
70
+ | 0.0216 | 6.9 | 9000 | 0.1409 | 0.1408 |
71
+ | 0.0146 | 7.36 | 9600 | 0.1524 | 0.1359 |
72
+ | 0.0133 | 7.82 | 10200 | 0.1494 | 0.1294 |
73
+ | 0.0103 | 8.28 | 10800 | 0.1600 | 0.1321 |
74
+ | 0.0079 | 8.74 | 11400 | 0.1658 | 0.1224 |
75
+ | 0.0065 | 9.2 | 12000 | 0.1644 | 0.1227 |
76
+ | 0.0043 | 9.66 | 12600 | 0.1771 | 0.1179 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dac1b981a7f42878872cc8d9d655a58bdf33fb3e4f48a88fd1e5f8b467cd01fc
3
  size 2423138460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:122698b8e975d90044fdf28f4ceae35bfe85bd61f128cb158e5b664cf7406623
3
  size 2423138460
runs/May22_10-29-23_kudsit-dgxserver/events.out.tfevents.1716354727.kudsit-dgxserver.3904209.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:088525f77cda2a1cd0ae48734623b0fb19cea58a71fe73d3c5170e1ddcb6e220
3
- size 17041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e46f4d150ff065d470c1e908ebffb10bad13e073e7798eb4a4bd21163646c102
3
+ size 17395