Hugging Face's logo

Gabi00
/
distil_whisper-en_students_test

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
English
whisper
Generated from Trainer
Eval Results
Inference Endpoints
Model card Files Metrics Community
Gabi00 commited on
Commit
68a5815
·
verified ·
1 Parent(s): 5f19c8d

End of training

Browse files
Files changed (4) hide show
  1. README.md +11 -10
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Jul01_09-34-10_8fe3014af66e/events.out.tfevents.1719826451.8fe3014af66e +2 -2
README.md CHANGED
@@ -24,7 +24,7 @@ model-index:
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 14.106315001840935
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 English-mistakes dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 0.5692
38
- - Wer: 14.1063
39
 
40
  ## Model description
41
 
@@ -68,16 +68,17 @@ The following hyperparameters were used during training:
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:------:|:----:|:---------------:|:-------:|
71
- | 0.651 | 0.5669 | 500 | 0.6500 | 15.1867 |
72
- | 0.4753 | 1.1338 | 1000 | 0.5997 | 14.6725 |
73
- | 0.4597 | 1.7007 | 1500 | 0.5794 | 13.8874 |
74
- | 0.3888 | 2.2676 | 2000 | 0.5737 | 13.8640 |
75
- | 0.3578 | 2.8345 | 2500 | 0.5692 | 14.1063 |
 
76
 
77
 
78
  ### Framework versions
79
 
80
- - Transformers 4.41.2
81
  - Pytorch 2.1.0+cu118
82
- - Datasets 2.19.2
83
  - Tokenizers 0.19.1
 
24
  metrics:
25
  - name: Wer
26
  type: wer
27
+ value: 13.110781686527167
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 English-mistakes dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.3784
38
+ - Wer: 13.1108
39
 
40
  ## Model description
41
 
 
68
 
69
  | Training Loss | Epoch | Step | Validation Loss | Wer |
70
  |:-------------:|:------:|:----:|:---------------:|:-------:|
71
+ | 0.6399 | 0.4444 | 500 | 0.4393 | 13.1649 |
72
+ | 0.526 | 0.8889 | 1000 | 0.4070 | 14.4792 |
73
+ | 0.4598 | 1.3333 | 1500 | 0.3948 | 14.2654 |
74
+ | 0.4094 | 1.7778 | 2000 | 0.3806 | 14.4050 |
75
+ | 0.3556 | 2.2222 | 2500 | 0.3816 | 13.2305 |
76
+ | 0.3304 | 2.6667 | 3000 | 0.3784 | 13.1108 |
77
 
78
 
79
  ### Framework versions
80
 
81
+ - Transformers 4.42.3
82
  - Pytorch 2.1.0+cu118
83
+ - Datasets 2.20.0
84
  - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -293,5 +293,5 @@
293
  "transcribe": 50360,
294
  "translate": 50359
295
  },
296
- "transformers_version": "4.41.2"
297
  }
 
293
  "transcribe": 50360,
294
  "translate": 50359
295
  },
296
+ "transformers_version": "4.42.3"
297
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:501f61c8eaddac1d9a0caa64ace6d68166540a71b84a1547b3a9ce77aa439d42
3
  size 3025686376
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ddee1c792b93325215cf4c2bef3cc5c04f73f5ebc90aa0076d7f8ebda8fc45
3
  size 3025686376
runs/Jul01_09-34-10_8fe3014af66e/events.out.tfevents.1719826451.8fe3014af66e CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9951ae07bce8599d8548c0a21b16f0e6e303700839871ef0a2eef1c97e0c607
3
- size 35783
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e15cbe70ff8f41e689c42f5cb4257483d609cb661f1231a19120a34290e551e4
3
+ size 36348