Hugging Face's logo

divakaivan
/
whisper-small-hi_test

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
divakaivan commited on
Commit
26cc696
•
1 Parent(s): 7776b89

End of training

Browse files
Files changed (3) hide show
  1. README.md +11 -11
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
README.md CHANGED
@@ -24,7 +24,7 @@ model-index:
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 22.39915074309979
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +34,8 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Glaswegian audio dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.7977
38
- - Wer: 22.3992
39
 
40
  ## Model description
41
 
@@ -66,17 +66,17 @@ The following hyperparameters were used during training:
66
 
67
  ### Training results
68
 
69
- | Training Loss | Epoch | Step | Validation Loss | Wer |
70
- |:-------------:|:--------:|:----:|:---------------:|:-------:|
71
- | 0.0012 | 25.6410 | 1000 | 0.7225 | 22.7176 |
72
- | 0.0062 | 51.2821 | 2000 | 0.7507 | 22.8238 |
73
- | 0.0001 | 76.9231 | 3000 | 0.7888 | 22.8238 |
74
- | 0.0 | 102.5641 | 4000 | 0.7977 | 22.3992 |
75
 
76
 
77
  ### Framework versions
78
 
79
- - Transformers 4.41.2
80
  - Pytorch 2.3.0+cu121
81
- - Datasets 2.19.2
82
  - Tokenizers 0.19.1
 
24
  metrics:
25
  - name: Wer
26
  type: wer
27
+ value: 24.51154529307282
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
34
 
35
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Glaswegian audio dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.9462
38
+ - Wer: 24.5115
39
 
40
  ## Model description
41
 
 
66
 
67
  ### Training results
68
 
69
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
70
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|
71
+ | 0.003 | 21.2766 | 1000 | 0.8488 | 31.4387 |
72
+ | 0.0029 | 42.5532 | 2000 | 0.9056 | 30.7282 |
73
+ | 0.0001 | 63.8298 | 3000 | 0.9364 | 24.4227 |
74
+ | 0.0001 | 85.1064 | 4000 | 0.9462 | 24.5115 |
75
 
76
 
77
  ### Framework versions
78
 
79
+ - Transformers 4.42.2
80
  - Pytorch 2.3.0+cu121
81
+ - Datasets 2.20.0
82
  - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -252,5 +252,5 @@
252
  "transcribe": 50359,
253
  "translate": 50358
254
  },
255
- "transformers_version": "4.41.2"
256
  }
 
252
  "transcribe": 50359,
253
  "translate": 50358
254
  },
255
+ "transformers_version": "4.42.2"
256
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d21001dc5674cf468a807dc68eff5ddd60944ecf279244151fdd88f4709277a
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73cd9eaa6c4ecc0f69968003540b74b47b8c731b1cee16b1a9ba940eca0f9cb0
3
  size 966995080