Hugging Face's logo

kiranpantha
/
w2v-bert-2.0-nepali-unlabeled-2

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
0ccbcb8
•
1 Parent(s): 29245aa

End of training

Browse files
Files changed (3) hide show
  1. README.md +133 -0
  2. model.safetensors +1 -1
  3. runs/Sep25_23-50-40_kiran/events.out.tfevents.1727287634.kiran.151812.0 +2 -2
README.md ADDED
@@ -0,0 +1,133 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - ne
5
+ license: mit
6
+ base_model: kiranpantha/w2v-bert-2.0-nepali-unlabeled-1
7
+ tags:
8
+ - generated_from_trainer
9
+ datasets:
10
+ - kiranpantha/OpenSLR54-Balanced-Nepali
11
+ metrics:
12
+ - wer
13
+ model-index:
14
+ - name: Wave2Vec2-Bert2.0 - Kiran Pantha
15
+ results:
16
+ - task:
17
+ name: Automatic Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: OpenSLR54
21
+ type: kiranpantha/OpenSLR54-Balanced-Nepali
22
+ config: default
23
+ split: test
24
+ args: 'config: ne, split: train,test'
25
+ metrics:
26
+ - name: Wer
27
+ type: wer
28
+ value: 0.44966842373745963
29
+ ---
30
+
31
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
32
+ should probably proofread and complete it, then remove this comment. -->
33
+
34
+ # Wave2Vec2-Bert2.0 - Kiran Pantha
35
+
36
+ This model is a fine-tuned version of [kiranpantha/w2v-bert-2.0-nepali-unlabeled-1](https://huggingface.co/kiranpantha/w2v-bert-2.0-nepali-unlabeled-1) on the OpenSLR54 dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 0.5190
39
+ - Wer: 0.4497
40
+ - Cer: 0.1090
41
+
42
+ ## Model description
43
+
44
+ More information needed
45
+
46
+ ## Intended uses & limitations
47
+
48
+ More information needed
49
+
50
+ ## Training and evaluation data
51
+
52
+ More information needed
53
+
54
+ ## Training procedure
55
+
56
+ ### Training hyperparameters
57
+
58
+ The following hyperparameters were used during training:
59
+ - learning_rate: 5e-05
60
+ - train_batch_size: 8
61
+ - eval_batch_size: 8
62
+ - seed: 42
63
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
+ - lr_scheduler_type: linear
65
+ - lr_scheduler_warmup_steps: 500
66
+ - num_epochs: 2
67
+ - mixed_precision_training: Native AMP
68
+
69
+ ### Training results
70
+
71
+ | Training Loss | Epoch | Step | Cer | Validation Loss | Wer |
72
+ |:-------------:|:------:|:-----:|:------:|:---------------:|:------:|
73
+ | 0.4494 | 0.0375 | 300 | 0.1147 | 0.5118 | 0.4793 |
74
+ | 0.5556 | 0.075 | 600 | 0.1448 | 0.6503 | 0.5808 |
75
+ | 0.5684 | 0.1125 | 900 | 0.1418 | 0.6258 | 0.5741 |
76
+ | 0.5309 | 0.15 | 1200 | 0.1446 | 0.6867 | 0.5391 |
77
+ | 0.615 | 0.1875 | 1500 | 0.1566 | 0.6692 | 0.5844 |
78
+ | 0.5627 | 0.225 | 1800 | 0.1434 | 0.6586 | 0.5597 |
79
+ | 0.6188 | 0.2625 | 2100 | 0.1500 | 0.6250 | 0.5559 |
80
+ | 0.5888 | 0.3 | 2400 | 0.1624 | 0.6863 | 0.6162 |
81
+ | 0.5435 | 0.3375 | 2700 | 0.1551 | 0.6415 | 0.5736 |
82
+ | 0.5667 | 0.375 | 3000 | 0.1478 | 0.6041 | 0.5661 |
83
+ | 0.5323 | 0.4125 | 3300 | 0.1392 | 0.5805 | 0.5327 |
84
+ | 0.5471 | 0.45 | 3600 | 0.1390 | 0.5699 | 0.5327 |
85
+ | 0.5939 | 0.4875 | 3900 | 0.1341 | 0.5739 | 0.5169 |
86
+ | 0.5795 | 0.525 | 4200 | 0.1392 | 0.6036 | 0.5278 |
87
+ | 0.4974 | 0.5625 | 4500 | 0.1255 | 0.5331 | 0.4997 |
88
+ | 0.5247 | 0.6 | 4800 | 0.1300 | 0.5649 | 0.5190 |
89
+ | 0.5035 | 0.6375 | 5100 | 0.1292 | 0.5583 | 0.5067 |
90
+ | 0.5354 | 0.675 | 5400 | 0.1270 | 0.5472 | 0.5115 |
91
+ | 0.536 | 0.7125 | 5700 | 0.1283 | 0.5406 | 0.5012 |
92
+ | 0.498 | 0.75 | 6000 | 0.1331 | 0.5747 | 0.5167 |
93
+ | 0.4339 | 0.7875 | 6300 | 0.1266 | 0.5224 | 0.4846 |
94
+ | 0.4504 | 0.825 | 6600 | 0.1234 | 0.5549 | 0.4982 |
95
+ | 0.4237 | 0.8625 | 6900 | 0.1221 | 0.5376 | 0.4759 |
96
+ | 0.4434 | 0.9 | 7200 | 0.1303 | 0.5651 | 0.5080 |
97
+ | 0.443 | 0.9375 | 7500 | 0.1219 | 0.5222 | 0.4889 |
98
+ | 0.4282 | 0.975 | 7800 | 0.1247 | 0.5297 | 0.4936 |
99
+ | 0.4128 | 1.0125 | 8100 | 0.1230 | 0.5263 | 0.4804 |
100
+ | 0.4507 | 1.05 | 8400 | 0.1254 | 0.5548 | 0.4881 |
101
+ | 0.4008 | 1.0875 | 8700 | 0.1232 | 0.5411 | 0.4816 |
102
+ | 0.4834 | 1.125 | 9000 | 0.1215 | 0.5264 | 0.4853 |
103
+ | 0.3955 | 1.1625 | 9300 | 0.1232 | 0.5288 | 0.4876 |
104
+ | 0.3837 | 1.2 | 9600 | 0.1224 | 0.5496 | 0.4853 |
105
+ | 0.3819 | 1.2375 | 9900 | 0.5215 | 0.4739 | 0.1232 |
106
+ | 0.3771 | 1.275 | 10200 | 0.5115 | 0.4641 | 0.1188 |
107
+ | 0.4067 | 1.3125 | 10500 | 0.5274 | 0.4810 | 0.1236 |
108
+ | 0.3561 | 1.35 | 10800 | 0.5366 | 0.4739 | 0.1182 |
109
+ | 0.3971 | 1.3875 | 11100 | 0.4951 | 0.4669 | 0.1178 |
110
+ | 0.337 | 1.425 | 11400 | 0.5180 | 0.4630 | 0.1156 |
111
+ | 0.4031 | 1.4625 | 11700 | 0.4895 | 0.4664 | 0.1156 |
112
+ | 0.4278 | 1.5 | 12000 | 0.4858 | 0.4469 | 0.1107 |
113
+ | 0.3332 | 1.5375 | 12300 | 0.4986 | 0.4546 | 0.1130 |
114
+ | 0.3516 | 1.575 | 12600 | 0.5067 | 0.4677 | 0.1148 |
115
+ | 0.4022 | 1.6125 | 12900 | 0.5022 | 0.4638 | 0.1114 |
116
+ | 0.3922 | 1.65 | 13200 | 0.4753 | 0.4588 | 0.1130 |
117
+ | 0.3483 | 1.6875 | 13500 | 0.4812 | 0.4562 | 0.1135 |
118
+ | 0.3572 | 1.725 | 13800 | 0.4940 | 0.4461 | 0.1083 |
119
+ | 0.2796 | 1.7625 | 14100 | 0.4854 | 0.4457 | 0.1082 |
120
+ | 0.2555 | 1.8 | 14400 | 0.5231 | 0.4482 | 0.1099 |
121
+ | 0.2823 | 1.8375 | 14700 | 0.5126 | 0.4475 | 0.1093 |
122
+ | 0.2478 | 1.875 | 15000 | 0.5063 | 0.4458 | 0.1087 |
123
+ | 0.2435 | 1.9125 | 15300 | 0.5151 | 0.4409 | 0.1077 |
124
+ | 0.2478 | 1.95 | 15600 | 0.5185 | 0.4464 | 0.1084 |
125
+ | 0.2653 | 1.9875 | 15900 | 0.5190 | 0.4497 | 0.1090 |
126
+
127
+
128
+ ### Framework versions
129
+
130
+ - Transformers 4.45.0.dev0
131
+ - Pytorch 2.4.1+cu121
132
+ - Datasets 2.21.0
133
+ - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ab9d126876dbf69b7eaccc8a8a3e593ad4288b4ad360743cd47034f663f6744
3
  size 2423081060
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0eace2ee8e5b068bbcb047d925c8780f5d190a9a625d53797f463e3dd6c3b9b9
3
  size 2423081060
runs/Sep25_23-50-40_kiran/events.out.tfevents.1727287634.kiran.151812.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d3e68b7a56b83e9eb0dbdb32dff0f8fffa812f446dd6d0359367ed68a64e1144
3
- size 17817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee762563956ef39469e19b5af89449a4e71fcb9ee220d5c555a730ed2ae7fdea
3
+ size 18747