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
6285703
·
verified ·
1 Parent(s): 8e26c26

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
  3. runs/May27_09-43-08_kudsit-dgxserver/events.out.tfevents.1716783948.kudsit-dgxserver.1401653.0 +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: 0.1679
21
- - Wer: 0.1214
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
- | 1.1162 | 0.46 | 600 | 0.4548 | 0.5036 |
57
- | 0.1745 | 0.92 | 1200 | 0.2634 | 0.3735 |
58
- | 0.1268 | 1.38 | 1800 | 0.2148 | 0.2951 |
59
- | 0.1106 | 1.84 | 2400 | 0.2106 | 0.2677 |
60
- | 0.0917 | 2.3 | 3000 | 0.1963 | 0.2466 |
61
- | 0.0794 | 2.76 | 3600 | 0.1789 | 0.2441 |
62
- | 0.0688 | 3.22 | 4200 | 0.1911 | 0.2371 |
63
- | 0.0586 | 3.68 | 4800 | 0.1774 | 0.2013 |
64
- | 0.0534 | 4.14 | 5400 | 0.1567 | 0.1876 |
65
- | 0.0417 | 4.6 | 6000 | 0.1733 | 0.1804 |
66
- | 0.0396 | 5.06 | 6600 | 0.1537 | 0.1595 |
67
- | 0.0302 | 5.52 | 7200 | 0.1559 | 0.1545 |
68
- | 0.03 | 5.98 | 7800 | 0.1482 | 0.1560 |
69
- | 0.0214 | 6.44 | 8400 | 0.1554 | 0.1622 |
70
- | 0.0209 | 6.9 | 9000 | 0.1464 | 0.1433 |
71
- | 0.015 | 7.36 | 9600 | 0.1626 | 0.1386 |
72
- | 0.0129 | 7.82 | 10200 | 0.1601 | 0.1331 |
73
- | 0.0105 | 8.28 | 10800 | 0.1651 | 0.1373 |
74
- | 0.0078 | 8.74 | 11400 | 0.1600 | 0.1237 |
75
- | 0.0061 | 9.2 | 12000 | 0.1694 | 0.1269 |
76
- | 0.004 | 9.66 | 12600 | 0.1679 | 0.1214 |
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: 0.1624
21
+ - Wer: 0.1242
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
56
+ | 1.1627 | 0.46 | 600 | 0.3628 | 0.4690 |
57
+ | 0.1739 | 0.92 | 1200 | 0.2809 | 0.3429 |
58
+ | 0.1254 | 1.38 | 1800 | 0.1997 | 0.2876 |
59
+ | 0.1083 | 1.84 | 2400 | 0.2066 | 0.2735 |
60
+ | 0.0917 | 2.3 | 3000 | 0.1918 | 0.2600 |
61
+ | 0.0778 | 2.76 | 3600 | 0.1739 | 0.2346 |
62
+ | 0.0685 | 3.22 | 4200 | 0.1629 | 0.2210 |
63
+ | 0.058 | 3.68 | 4800 | 0.1641 | 0.1983 |
64
+ | 0.053 | 4.14 | 5400 | 0.1557 | 0.1841 |
65
+ | 0.0417 | 4.6 | 6000 | 0.1464 | 0.1928 |
66
+ | 0.0385 | 5.06 | 6600 | 0.1448 | 0.1610 |
67
+ | 0.0303 | 5.52 | 7200 | 0.1591 | 0.1510 |
68
+ | 0.0303 | 5.98 | 7800 | 0.1352 | 0.1510 |
69
+ | 0.0212 | 6.44 | 8400 | 0.1376 | 0.1473 |
70
+ | 0.0208 | 6.9 | 9000 | 0.1335 | 0.1314 |
71
+ | 0.0153 | 7.36 | 9600 | 0.1455 | 0.1411 |
72
+ | 0.0134 | 7.82 | 10200 | 0.1414 | 0.1403 |
73
+ | 0.0109 | 8.28 | 10800 | 0.1440 | 0.1361 |
74
+ | 0.008 | 8.74 | 11400 | 0.1499 | 0.1286 |
75
+ | 0.006 | 9.2 | 12000 | 0.1597 | 0.1212 |
76
+ | 0.0039 | 9.66 | 12600 | 0.1624 | 0.1242 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ce6e48a6d636eb69397036ab1771ee3c615b4174ce8e95be1a8ddfe261d790b
3
  size 2423138460
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f7bcc2dfc933849bfc19a18882fd5d6695eb6fed8c23f25d4b2a70b13a6bebc
3
  size 2423138460
runs/May27_09-43-08_kudsit-dgxserver/events.out.tfevents.1716783948.kudsit-dgxserver.1401653.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77f9c6ecfae6081acae3a4a3bd9196dfade7a433cc1840166e484ee79712581a
3
- size 17041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1827e5e3a65d93cba9b12b1b9658d2fb7b6a2b67df5cbc569e362f6c7c24c8
3
+ size 17395