Hugging Face's logo

ShayanKKK
/
whisper-small-hi

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Hindi
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
ShayanKKK commited on
Commit
bd54505
•
1 Parent(s): 7785ce4

End of training

Browse files
Files changed (4) hide show
  1. README.md +6 -6
  2. model.safetensors +1 -1
  3. runs/Oct03_17-29-27_gashtasb/events.out.tfevents.1727976569.gashtasb.277328.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -25,7 +25,7 @@ model-index:
25
  metrics:
26
  - name: Wer
27
  type: wer
28
- value: 45.834084886157086
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -36,7 +36,7 @@ should probably proofread and complete it, then remove this comment. -->
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
37
  It achieves the following results on the evaluation set:
38
  - Loss: 0.4497
39
- - Wer: 45.8341
40
 
41
  ## Model description
42
 
@@ -70,10 +70,10 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer |
72
  |:-------------:|:------:|:----:|:---------------:|:-------:|
73
- | 0.3698 | 0.1074 | 1000 | 0.6211 | 55.1344 |
74
- | 0.2768 | 0.2148 | 2000 | 0.5376 | 50.4502 |
75
- | 0.2718 | 0.3222 | 3000 | 0.4804 | 45.7730 |
76
- | 0.2556 | 0.4296 | 4000 | 0.4497 | 45.8341 |
77
 
78
 
79
  ### Framework versions
 
25
  metrics:
26
  - name: Wer
27
  type: wer
28
+ value: 45.41784024530684
29
  ---
30
 
31
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
36
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
37
  It achieves the following results on the evaluation set:
38
  - Loss: 0.4497
39
+ - Wer: 45.4178
40
 
41
  ## Model description
42
 
 
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Wer |
72
  |:-------------:|:------:|:----:|:---------------:|:-------:|
73
+ | 0.3713 | 0.1074 | 1000 | 0.6230 | 55.3494 |
74
+ | 0.2776 | 0.2148 | 2000 | 0.5377 | 50.2837 |
75
+ | 0.2702 | 0.3222 | 3000 | 0.4806 | 45.9243 |
76
+ | 0.2551 | 0.4296 | 4000 | 0.4497 | 45.4178 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d857fa6ec1b5943f4b198125a893d2768fc0e5b360cb028f7dd302bc802fdbc
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ae80d157e7491f2651e9589bb15453ec334a3fc8b85615f7b6243a14b36f447
3
  size 966995080
runs/Oct03_17-29-27_gashtasb/events.out.tfevents.1727976569.gashtasb.277328.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4a233e037bcae721dbcc8c943536bd45afdfd364ff08c8e79073b6f0535d24
3
+ size 42067
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d52ee9fdcfd2a30b92fcbd74f5a7624a371e4a2bf82c242b80acfa7cc0188dc8
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b43e540d6a6208834a5c6780edfc18780aa82f3f5e9ef13eacb6eb2492a67c93
3
  size 5368