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
10f12c0
•
1 Parent(s): 95639eb

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
  3. runs/May13_09-22-04_kudsit-dgxserver/events.out.tfevents.1715573081.kudsit-dgxserver.3533552.0 +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: 0.1641
21
- - Wer: 0.1184
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
- | 1.1077 | 0.46 | 600 | 0.4029 | 0.4897 |
57
- | 0.1727 | 0.92 | 1200 | 0.2339 | 0.3573 |
58
- | 0.1224 | 1.38 | 1800 | 0.2159 | 0.3225 |
59
- | 0.1103 | 1.84 | 2400 | 0.1838 | 0.2764 |
60
- | 0.0907 | 2.3 | 3000 | 0.1844 | 0.2603 |
61
- | 0.0796 | 2.76 | 3600 | 0.1829 | 0.2498 |
62
- | 0.0685 | 3.22 | 4200 | 0.1719 | 0.2336 |
63
- | 0.0588 | 3.68 | 4800 | 0.1607 | 0.2030 |
64
- | 0.054 | 4.14 | 5400 | 0.1611 | 0.1941 |
65
- | 0.0424 | 4.6 | 6000 | 0.1536 | 0.1821 |
66
- | 0.0402 | 5.06 | 6600 | 0.1562 | 0.1769 |
67
- | 0.0312 | 5.52 | 7200 | 0.1494 | 0.1655 |
68
- | 0.0303 | 5.98 | 7800 | 0.1471 | 0.1510 |
69
- | 0.0218 | 6.44 | 8400 | 0.1707 | 0.1488 |
70
- | 0.0218 | 6.9 | 9000 | 0.1458 | 0.1296 |
71
- | 0.0151 | 7.36 | 9600 | 0.1424 | 0.1326 |
72
- | 0.014 | 7.82 | 10200 | 0.1406 | 0.1266 |
73
- | 0.0107 | 8.28 | 10800 | 0.1476 | 0.1291 |
74
- | 0.0078 | 8.74 | 11400 | 0.1563 | 0.1254 |
75
- | 0.007 | 9.2 | 12000 | 0.1528 | 0.1197 |
76
- | 0.0041 | 9.66 | 12600 | 0.1641 | 0.1184 |
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: 0.1651
21
+ - Wer: 0.1279
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
56
+ | 1.4399 | 0.46 | 600 | 0.3709 | 0.4586 |
57
+ | 0.1715 | 0.92 | 1200 | 0.2427 | 0.3379 |
58
+ | 0.1226 | 1.38 | 1800 | 0.2216 | 0.2919 |
59
+ | 0.1073 | 1.84 | 2400 | 0.1992 | 0.2672 |
60
+ | 0.0888 | 2.3 | 3000 | 0.1835 | 0.2506 |
61
+ | 0.0781 | 2.76 | 3600 | 0.1768 | 0.2491 |
62
+ | 0.0671 | 3.22 | 4200 | 0.1702 | 0.2309 |
63
+ | 0.0575 | 3.68 | 4800 | 0.1784 | 0.2202 |
64
+ | 0.0531 | 4.14 | 5400 | 0.1690 | 0.1881 |
65
+ | 0.0421 | 4.6 | 6000 | 0.1707 | 0.1876 |
66
+ | 0.0398 | 5.06 | 6600 | 0.1672 | 0.1759 |
67
+ | 0.0305 | 5.52 | 7200 | 0.1516 | 0.1575 |
68
+ | 0.0306 | 5.98 | 7800 | 0.1576 | 0.1682 |
69
+ | 0.0219 | 6.44 | 8400 | 0.1516 | 0.1610 |
70
+ | 0.021 | 6.9 | 9000 | 0.1418 | 0.1493 |
71
+ | 0.0151 | 7.36 | 9600 | 0.1343 | 0.1359 |
72
+ | 0.0133 | 7.82 | 10200 | 0.1410 | 0.1433 |
73
+ | 0.0103 | 8.28 | 10800 | 0.1564 | 0.1386 |
74
+ | 0.0084 | 8.74 | 11400 | 0.1546 | 0.1276 |
75
+ | 0.0067 | 9.2 | 12000 | 0.1622 | 0.1244 |
76
+ | 0.0043 | 9.66 | 12600 | 0.1651 | 0.1279 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25e8a58f70b8d824f0a475f091103b06391adb3c70d9cb48a47d9c5784f2c711
3
  size 2423138460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07df054f048c5f0b391dc1bdec2a559d99256bd41223d7da516fe9c8adf415c8
3
  size 2423138460
runs/May13_09-22-04_kudsit-dgxserver/events.out.tfevents.1715573081.kudsit-dgxserver.3533552.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17eb43a874b32d1feeb305f709925748752369eb1ab54ad9def066913d6bdd27
3
- size 17041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43ff1751a712427ccaf9e5b9ca4b78e90d7a9573b3a53c08a304846dc8af121d
3
+ size 17395