Hugging Face's logo

kiranpantha
/
w2v-bert-2.0-nepali

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Nepali
wav2vec2-bert
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
kiranpantha commited on
Commit
1cc0b16
•
1 Parent(s): 7b95b3f

End of training

Browse files
Files changed (3) hide show
  1. README.md +28 -16
  2. model.safetensors +1 -1
  3. runs/Sep25_01-33-32_kiran/events.out.tfevents.1727207389.kiran.143682.0 +2 -2
README.md CHANGED
@@ -25,7 +25,7 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 0.2604166666666667
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,8 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the OpenSLR54 dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.2182
39
- - Wer: 0.2604
 
40
 
41
  ## Model description
42
 
@@ -67,19 +68,30 @@ The following hyperparameters were used during training:
67
 
68
  ### Training results
69
 
70
- | Training Loss | Epoch | Step | Validation Loss | Wer |
71
- |:-------------:|:------:|:----:|:---------------:|:------:|
72
- | 4.4889 | 0.1800 | 300 | 0.8423 | 0.8076 |
73
- | 0.7028 | 0.3599 | 600 | 0.6309 | 0.5951 |
74
- | 0.5787 | 0.5399 | 900 | 0.5455 | 0.5167 |
75
- | 0.476 | 0.7199 | 1200 | 0.4670 | 0.5109 |
76
- | 0.4094 | 0.8998 | 1500 | 0.4415 | 0.4382 |
77
- | 0.3345 | 1.0798 | 1800 | 0.3395 | 0.3951 |
78
- | 0.2545 | 1.2597 | 2100 | 0.3266 | 0.3609 |
79
- | 0.2444 | 1.4397 | 2400 | 0.2814 | 0.3204 |
80
- | 0.2214 | 1.6197 | 2700 | 0.2593 | 0.2947 |
81
- | 0.1846 | 1.7996 | 3000 | 0.2256 | 0.2685 |
82
- | 0.1783 | 1.9796 | 3300 | 0.2182 | 0.2604 |
 
 
 
 
 
 
 
 
 
 
 
83
 
84
 
85
  ### Framework versions
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 0.25254629629629627
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
35
 
36
  This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the OpenSLR54 dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.2212
39
+ - Wer: 0.2525
40
+ - Cer: 0.0565
41
 
42
  ## Model description
43
 
 
68
 
69
  ### Training results
70
 
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
72
+ |:-------------:|:------:|:----:|:---------------:|:------:|:------:|
73
+ | 0.4436 | 0.0900 | 300 | 0.5638 | 0.5560 | 0.1447 |
74
+ | 0.5495 | 0.1800 | 600 | 0.6876 | 0.6171 | 0.1641 |
75
+ | 0.6148 | 0.2699 | 900 | 0.6872 | 0.6211 | 0.1724 |
76
+ | 0.564 | 0.3599 | 1200 | 0.5503 | 0.5162 | 0.1326 |
77
+ | 0.4964 | 0.4499 | 1500 | 0.5831 | 0.5319 | 0.1318 |
78
+ | 0.4437 | 0.5399 | 1800 | 0.4913 | 0.4935 | 0.1202 |
79
+ | 0.4441 | 0.6299 | 2100 | 0.4754 | 0.4764 | 0.1193 |
80
+ | 0.3861 | 0.7199 | 2400 | 0.4357 | 0.4361 | 0.1055 |
81
+ | 0.3811 | 0.8098 | 2700 | 0.4282 | 0.4137 | 0.0976 |
82
+ | 0.3754 | 0.8998 | 3000 | 0.3905 | 0.4069 | 0.0975 |
83
+ | 0.3511 | 0.9898 | 3300 | 0.3547 | 0.3692 | 0.0863 |
84
+ | 0.2496 | 1.0798 | 3600 | 0.3297 | 0.3433 | 0.0796 |
85
+ | 0.242 | 1.1698 | 3900 | 0.3125 | 0.3315 | 0.0770 |
86
+ | 0.2378 | 1.2597 | 4200 | 0.3158 | 0.3336 | 0.0757 |
87
+ | 0.2274 | 1.3497 | 4500 | 0.2871 | 0.3097 | 0.0722 |
88
+ | 0.2142 | 1.4397 | 4800 | 0.3010 | 0.3058 | 0.0712 |
89
+ | 0.1949 | 1.5297 | 5100 | 0.2767 | 0.2944 | 0.0678 |
90
+ | 0.198 | 1.6197 | 5400 | 0.2487 | 0.2824 | 0.0639 |
91
+ | 0.1806 | 1.7097 | 5700 | 0.2376 | 0.2674 | 0.0612 |
92
+ | 0.1675 | 1.7996 | 6000 | 0.2293 | 0.2630 | 0.0595 |
93
+ | 0.1671 | 1.8896 | 6300 | 0.2248 | 0.2581 | 0.0576 |
94
+ | 0.1526 | 1.9796 | 6600 | 0.2212 | 0.2525 | 0.0565 |
95
 
96
 
97
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:94a4ce0010a944a40e42059b76cb8e4f5f305e744ff80c0e31db79082e4fbc6e
3
  size 2423081060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c2fccb891a148e00b0e17631cd37c2153609202104ee216c247fe4f63acd3bf
3
  size 2423081060
runs/Sep25_01-33-32_kiran/events.out.tfevents.1727207389.kiran.143682.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:538f54f75bebdde97585e51f800f1d1dacd04b10b513118d716d1310d8f110b8
3
- size 26213
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:835ed9d28bdede02735d0f3f4b9c80e69842ac3a4b1f8b9dd33d14452505a3a4
3
+ size 26567