Hugging Face's logo

rajvs20
/
whisper-small-dv

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Divehi
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
rajvs20 commited on
Commit
34356ff
•
1 Parent(s): 78e147a

End of training

Browse files
Files changed (2) hide show
  1. README.md +15 -8
  2. model.safetensors +1 -1
README.md CHANGED
@@ -25,7 +25,7 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 13.473241297770977
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
35
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
37
  It achieves the following results on the evaluation set:
38
- - Loss: 0.1727
39
- - Wer Ortho: 62.7690
40
- - Wer: 13.4732
41
 
42
  ## Model description
43
 
@@ -63,14 +63,21 @@ The following hyperparameters were used during training:
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: constant_with_warmup
65
  - lr_scheduler_warmup_steps: 50
66
- - training_steps: 500
67
  - mixed_precision_training: Native AMP
68
 
69
  ### Training results
70
 
71
- | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
72
- |:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
73
- | 0.1207 | 1.6287 | 500 | 0.1727 | 62.7690 | 13.4732 |
 
 
 
 
 
 
 
74
 
75
 
76
  ### Framework versions
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 11.039051361407658
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 [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 13 dataset.
37
  It achieves the following results on the evaluation set:
38
+ - Loss: 0.2938
39
+ - Wer Ortho: 57.8522
40
+ - Wer: 11.0391
41
 
42
  ## Model description
43
 
 
63
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
64
  - lr_scheduler_type: constant_with_warmup
65
  - lr_scheduler_warmup_steps: 50
66
+ - training_steps: 4000
67
  - mixed_precision_training: Native AMP
68
 
69
  ### Training results
70
 
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer |
72
+ |:-------------:|:-------:|:----:|:---------------:|:---------:|:-------:|
73
+ | 0.0596 | 1.6287 | 500 | 0.1694 | 61.1045 | 11.9414 |
74
+ | 0.021 | 3.2573 | 1000 | 0.1984 | 57.7547 | 11.6598 |
75
+ | 0.0168 | 4.8860 | 1500 | 0.2246 | 58.1378 | 11.6546 |
76
+ | 0.0079 | 6.5147 | 2000 | 0.2520 | 57.3508 | 11.2216 |
77
+ | 0.0056 | 8.1433 | 2500 | 0.2669 | 57.9079 | 11.2042 |
78
+ | 0.0049 | 9.7720 | 3000 | 0.2751 | 57.1419 | 11.1573 |
79
+ | 0.0047 | 11.4007 | 3500 | 0.2803 | 56.9956 | 11.0269 |
80
+ | 0.0044 | 13.0293 | 4000 | 0.2938 | 57.8522 | 11.0391 |
81
 
82
 
83
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aa3e47a96f1f84fa51d5f43d03419a409a4aad19ea309c33abbb70ec5899674
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c281c65cdb459a117c4525f7b60493da7d964edba284d96416ce365a3947e02a
3
  size 966995080