prakanda commited on
Commit
b588d31
·
verified ·
1 Parent(s): 45b336f

End of training

Browse files
Files changed (2) hide show
  1. README.md +27 -2
  2. model.safetensors +1 -1
README.md CHANGED
@@ -8,9 +8,24 @@ tags:
8
  - generated_from_trainer
9
  datasets:
10
  - mozilla-foundation/common_voice_17_0
 
 
11
  model-index:
12
  - name: Whisper Tiny Nepali
13
- results: []
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -19,6 +34,9 @@ should probably proofread and complete it, then remove this comment. -->
19
  # Whisper Tiny Nepali
20
 
21
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 17.0 dataset.
 
 
 
22
 
23
  ## Model description
24
 
@@ -46,11 +64,18 @@ The following hyperparameters were used during training:
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
  - lr_scheduler_warmup_steps: 500
49
- - training_steps: 5
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
 
 
 
 
 
 
 
54
 
55
 
56
  ### Framework versions
 
8
  - generated_from_trainer
9
  datasets:
10
  - mozilla-foundation/common_voice_17_0
11
+ metrics:
12
+ - wer
13
  model-index:
14
  - name: Whisper Tiny Nepali
15
+ results:
16
+ - task:
17
+ name: Automatic Speech Recognition
18
+ type: automatic-speech-recognition
19
+ dataset:
20
+ name: Common Voice 17.0
21
+ type: mozilla-foundation/common_voice_17_0
22
+ config: ne-NP
23
+ split: test
24
+ args: 'config: ne-NP, split: train+validation'
25
+ metrics:
26
+ - name: Wer
27
+ type: wer
28
+ value: 81.72804532577904
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
34
  # Whisper Tiny Nepali
35
 
36
  This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 17.0 dataset.
37
+ It achieves the following results on the evaluation set:
38
+ - Loss: 1.5772
39
+ - Wer: 81.7280
40
 
41
  ## Model description
42
 
 
64
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
65
  - lr_scheduler_type: linear
66
  - lr_scheduler_warmup_steps: 500
67
+ - training_steps: 5000
68
  - mixed_precision_training: Native AMP
69
 
70
  ### Training results
71
 
72
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
73
+ |:-------------:|:--------:|:----:|:---------------:|:-------:|
74
+ | 0.0042 | 32.2623 | 1000 | 1.1940 | 81.7280 |
75
+ | 0.0002 | 64.5246 | 2000 | 1.4012 | 81.3739 |
76
+ | 0.0001 | 96.7869 | 3000 | 1.4975 | 82.0822 |
77
+ | 0.0001 | 129.0328 | 4000 | 1.5517 | 81.8697 |
78
+ | 0.0001 | 161.2951 | 5000 | 1.5772 | 81.7280 |
79
 
80
 
81
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ba7e2bfbba4283ec42832a71a18bbff2d640d1e8e7d139eaba56e6fef05cc812
3
  size 151061672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51ac2c8e33d679067ed540a55281cbe59e944595def1117b700fc8903ebaa71b
3
  size 151061672