kneth90 commited on
Commit
7a7a643
·
verified ·
1 Parent(s): f9d096a

End of training

Browse files
README.md CHANGED
@@ -23,7 +23,7 @@ model-index:
23
  metrics:
24
  - name: Wer
25
  type: wer
26
- value: 62.0253164556962
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
33
 
34
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Test Dataset 2 dataset.
35
  It achieves the following results on the evaluation set:
36
- - Loss: 1.5890
37
- - Wer: 62.0253
38
 
39
  ## Model description
40
 
@@ -67,15 +67,15 @@ The following hyperparameters were used during training:
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:--------:|:----:|:---------------:|:-------:|
70
- | 0.0012 | 41.6667 | 1000 | 1.4854 | 64.1350 |
71
- | 0.0001 | 83.3333 | 2000 | 1.5412 | 62.2363 |
72
- | 0.0 | 125.0 | 3000 | 1.5755 | 62.0253 |
73
- | 0.0 | 166.6667 | 4000 | 1.5890 | 62.0253 |
74
 
75
 
76
  ### Framework versions
77
 
78
- - Transformers 4.47.0
79
  - Pytorch 2.5.1+cu124
80
  - Datasets 3.2.0
81
  - Tokenizers 0.21.0
 
23
  metrics:
24
  - name: Wer
25
  type: wer
26
+ value: 63.92405063291139
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
33
 
34
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Test Dataset 2 dataset.
35
  It achieves the following results on the evaluation set:
36
+ - Loss: 1.6740
37
+ - Wer: 63.9241
38
 
39
  ## Model description
40
 
 
67
 
68
  | Training Loss | Epoch | Step | Validation Loss | Wer |
69
  |:-------------:|:--------:|:----:|:---------------:|:-------:|
70
+ | 0.0008 | 41.6667 | 1000 | 1.5316 | 64.9789 |
71
+ | 0.0001 | 83.3333 | 2000 | 1.6316 | 64.3460 |
72
+ | 0.0 | 125.0 | 3000 | 1.6618 | 64.5570 |
73
+ | 0.0 | 166.6667 | 4000 | 1.6740 | 63.9241 |
74
 
75
 
76
  ### Framework versions
77
 
78
+ - Transformers 4.47.1
79
  - Pytorch 2.5.1+cu124
80
  - Datasets 3.2.0
81
  - Tokenizers 0.21.0
generation_config.json CHANGED
@@ -250,5 +250,5 @@
250
  "transcribe": 50359,
251
  "translate": 50358
252
  },
253
- "transformers_version": "4.47.0"
254
  }
 
250
  "transcribe": 50359,
251
  "translate": 50358
252
  },
253
+ "transformers_version": "4.47.1"
254
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b804b3bce4bb832397d6fd65d91fefb9d60cc53b1140deb9e4291dcc0744fc8
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc8331c02320b08800cb5777f59c7aac81fbc47eb21cfbdf4668f807c17fbc2e
3
  size 966995080
runs/Dec30_15-01-28_msi/events.out.tfevents.1735545692.msi.11149.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f7f06e8c752ba83e27d1479aa5a92c0762886d0f30ab3f96cc06d14c51032d14
3
- size 33063
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac38c03862c293a4886f23c56d3386ba7b97bc046ccceb8ce1cc061de28f2762
3
+ size 42175