Hugging Face's logo

kavyamanohar
/
whisper-poula-asr

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Poumei Naga
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
kavyamanohar commited on
Commit
65e931e
·
verified ·
1 Parent(s): 0d73154

End of training

Browse files
Files changed (3) hide show
  1. README.md +10 -10
  2. model.safetensors +1 -1
  3. runs/Oct12_15-48-44_d7097a64654f/events.out.tfevents.1728748126.d7097a64654f.980.0 +2 -2
README.md CHANGED
@@ -22,7 +22,7 @@ model-index:
22
  metrics:
23
  - name: Wer
24
  type: wer
25
- value: 96.50924024640656
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -32,8 +32,8 @@ should probably proofread and complete it, then remove this comment. -->
32
 
33
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Paula dataset.
34
  It achieves the following results on the evaluation set:
35
- - Loss: 4.0024
36
- - Wer: 96.5092
37
 
38
  ## Model description
39
 
@@ -64,13 +64,13 @@ The following hyperparameters were used during training:
64
 
65
  ### Training results
66
 
67
- | Training Loss | Epoch | Step | Validation Loss | Wer |
68
- |:-------------:|:-----:|:----:|:---------------:|:-------:|
69
- | 0.3865 | 10.0 | 200 | 3.3504 | 96.7146 |
70
- | 0.0139 | 20.0 | 400 | 3.7153 | 96.5092 |
71
- | 0.0015 | 30.0 | 600 | 3.9040 | 95.8932 |
72
- | 0.0009 | 40.0 | 800 | 3.9813 | 97.1253 |
73
- | 0.0008 | 50.0 | 1000 | 4.0024 | 96.5092 |
74
 
75
 
76
  ### Framework versions
 
22
  metrics:
23
  - name: Wer
24
  type: wer
25
+ value: 102.84463894967178
26
  ---
27
 
28
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
32
 
33
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Paula dataset.
34
  It achieves the following results on the evaluation set:
35
+ - Loss: 3.1674
36
+ - Wer: 102.8446
37
 
38
  ## Model description
39
 
 
64
 
65
  ### Training results
66
 
67
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
68
+ |:-------------:|:-----:|:----:|:---------------:|:--------:|
69
+ | 0.3851 | 10.0 | 200 | 2.6828 | 101.7505 |
70
+ | 0.0097 | 20.0 | 400 | 2.9628 | 101.5317 |
71
+ | 0.002 | 30.0 | 600 | 3.1073 | 100.2188 |
72
+ | 0.001 | 40.0 | 800 | 3.1528 | 101.9694 |
73
+ | 0.0008 | 50.0 | 1000 | 3.1674 | 102.8446 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a51ed0198dcf373d5f19b0d278f38cfbe99a196ee2083790a3f4a36b828bd5d
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d64dba4fca2971a7ea8e8cf99d92a4df8894d358668d83c2362d21f2ab8b564
3
  size 966995080
runs/Oct12_15-48-44_d7097a64654f/events.out.tfevents.1728748126.d7097a64654f.980.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ef8f67704dfd026b95c5abb8c577c503cc7d64bfab63631e74216bda3e8f0ef
3
- size 15845
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c81d7d6ad6faf5392292ab1245672b9a316b17c83699e7f48d8bb7d20d84c0
3
+ size 16199