Hugging Face's logo

Bajiyo
/
w2v-bert-2.0-malayalam_mixeddataset_thre

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
wav2vec2-bert
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Bajiyo commited on
Commit
4fb8a5c
•
1 Parent(s): 7c182d7

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -24
  2. model.safetensors +1 -1
  3. runs/Apr30_09-50-59_kudsit-dgxserver/events.out.tfevents.1714451870.kudsit-dgxserver.914216.0 +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-malayalam_mixeddataset_thre
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: 0.1771
21
- - Wer: 0.1202
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
- | 1.0443 | 0.47 | 600 | 0.3525 | 0.4596 |
57
- | 0.167 | 0.95 | 1200 | 0.2856 | 0.3824 |
58
- | 0.12 | 1.42 | 1800 | 0.2161 | 0.2978 |
59
- | 0.1027 | 1.9 | 2400 | 0.1963 | 0.2640 |
60
- | 0.0811 | 2.37 | 3000 | 0.2021 | 0.2356 |
61
- | 0.0733 | 2.85 | 3600 | 0.1791 | 0.2272 |
62
- | 0.0634 | 3.32 | 4200 | 0.1569 | 0.2003 |
63
- | 0.054 | 3.8 | 4800 | 0.1760 | 0.2110 |
64
- | 0.0442 | 4.27 | 5400 | 0.1789 | 0.1889 |
65
- | 0.0385 | 4.74 | 6000 | 0.1634 | 0.1774 |
66
- | 0.0358 | 5.22 | 6600 | 0.1583 | 0.1573 |
67
- | 0.0282 | 5.69 | 7200 | 0.1573 | 0.1570 |
68
- | 0.0243 | 6.17 | 7800 | 0.1539 | 0.1545 |
69
- | 0.0199 | 6.64 | 8400 | 0.1653 | 0.1505 |
70
- | 0.017 | 7.12 | 9000 | 0.1525 | 0.1299 |
71
- | 0.0127 | 7.59 | 9600 | 0.1524 | 0.1336 |
72
- | 0.0125 | 8.07 | 10200 | 0.1595 | 0.1291 |
73
- | 0.0079 | 8.54 | 10800 | 0.1598 | 0.1254 |
74
- | 0.0074 | 9.02 | 11400 | 0.1570 | 0.1254 |
75
- | 0.0039 | 9.49 | 12000 | 0.1746 | 0.1222 |
76
- | 0.0039 | 9.96 | 12600 | 0.1771 | 0.1202 |
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-malayalam_mixeddataset_thre
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: 0.1707
21
+ - Wer: 0.1157
22
 
23
  ## Model description
24
 
 
53
 
54
  | Training Loss | Epoch | Step | Validation Loss | Wer |
55
  |:-------------:|:-----:|:-----:|:---------------:|:------:|
56
+ | 1.0465 | 0.47 | 600 | 0.3707 | 0.4561 |
57
+ | 0.167 | 0.95 | 1200 | 0.2639 | 0.3710 |
58
+ | 0.1209 | 1.42 | 1800 | 0.2276 | 0.3143 |
59
+ | 0.1028 | 1.9 | 2400 | 0.2139 | 0.2657 |
60
+ | 0.0831 | 2.37 | 3000 | 0.2015 | 0.2553 |
61
+ | 0.0746 | 2.85 | 3600 | 0.1729 | 0.2374 |
62
+ | 0.0626 | 3.32 | 4200 | 0.1501 | 0.2192 |
63
+ | 0.0547 | 3.8 | 4800 | 0.1824 | 0.2217 |
64
+ | 0.0448 | 4.27 | 5400 | 0.1571 | 0.1747 |
65
+ | 0.0383 | 4.74 | 6000 | 0.1438 | 0.1662 |
66
+ | 0.0353 | 5.22 | 6600 | 0.1476 | 0.1657 |
67
+ | 0.029 | 5.69 | 7200 | 0.1543 | 0.1655 |
68
+ | 0.025 | 6.17 | 7800 | 0.1620 | 0.1553 |
69
+ | 0.02 | 6.64 | 8400 | 0.1481 | 0.1468 |
70
+ | 0.0167 | 7.12 | 9000 | 0.1501 | 0.1376 |
71
+ | 0.0126 | 7.59 | 9600 | 0.1469 | 0.1341 |
72
+ | 0.0122 | 8.07 | 10200 | 0.1565 | 0.1291 |
73
+ | 0.0079 | 8.54 | 10800 | 0.1592 | 0.1242 |
74
+ | 0.0073 | 9.02 | 11400 | 0.1594 | 0.1237 |
75
+ | 0.0039 | 9.49 | 12000 | 0.1710 | 0.1204 |
76
+ | 0.0039 | 9.96 | 12600 | 0.1707 | 0.1157 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4dcdd126f0b9aff6927578db1404ab6a455e86e1b55e87602eeeb38e4d9d196b
3
  size 2423130260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b51250db925f649a845c5967b9148eeb3478e0b087f6f1cede870d88251299be
3
  size 2423130260
runs/Apr30_09-50-59_kudsit-dgxserver/events.out.tfevents.1714451870.kudsit-dgxserver.914216.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:048b2ae9ac64a1b5ea89fef8e6f9cc6dc26333dd8a2a1abefdcbd193f85d9a91
3
- size 17041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef141354cc2c5374895f1ab47c3bb405ef3f08ef7b611d4cb7e0a28e3a199a5
3
+ size 17395