Hugging Face's logo

Oyounghyun
/
contents

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Oyounghyun commited on
Commit
0936a3d
•
1 Parent(s): b8db4ba

End of training

Browse files
Files changed (4) hide show
  1. README.md +28 -28
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Jun28_01-14-22_8bc15a111634/events.out.tfevents.1719537268.8bc15a111634.245.0 +2 -2
README.md CHANGED
@@ -1,13 +1,13 @@
1
  ---
2
- base_model: openai/whisper-base
3
- datasets:
4
- - Oyounghyun/whisper_study_data
5
  language:
6
  - ko
7
  license: apache-2.0
 
8
  tags:
9
  - hf-asr-leaderboard
10
  - generated_from_trainer
 
 
11
  model-index:
12
  - name: study0627
13
  results: []
@@ -20,8 +20,8 @@ should probably proofread and complete it, then remove this comment. -->
20
 
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the train dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 2.2804
24
- - Cer: 111.1239
25
 
26
  ## Model description
27
 
@@ -52,33 +52,33 @@ The following hyperparameters were used during training:
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Cer |
56
- |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
- | 2.0845 | 3.8462 | 100 | 2.2118 | 776.7723 |
58
- | 1.3061 | 7.6923 | 200 | 1.8671 | 197.1758 |
59
- | 0.8206 | 11.5385 | 300 | 1.8098 | 305.6484 |
60
- | 0.4922 | 15.3846 | 400 | 1.8203 | 165.5908 |
61
- | 0.2646 | 19.2308 | 500 | 1.8687 | 171.3545 |
62
- | 0.1408 | 23.0769 | 600 | 1.9448 | 124.7262 |
63
- | 0.0696 | 26.9231 | 700 | 1.9645 | 145.9942 |
64
- | 0.0407 | 30.7692 | 800 | 2.0531 | 128.3573 |
65
- | 0.0194 | 34.6154 | 900 | 2.0781 | 101.7867 |
66
- | 0.0103 | 38.4615 | 1000 | 2.1384 | 140.1153 |
67
- | 0.0052 | 42.3077 | 1100 | 2.1840 | 117.4063 |
68
- | 0.0036 | 46.1538 | 1200 | 2.2111 | 116.3112 |
69
- | 0.0029 | 50.0 | 1300 | 2.2287 | 114.2939 |
70
- | 0.0025 | 53.8462 | 1400 | 2.2440 | 116.8300 |
71
- | 0.0022 | 57.6923 | 1500 | 2.2549 | 113.8905 |
72
- | 0.002 | 61.5385 | 1600 | 2.2652 | 112.9107 |
73
- | 0.0018 | 65.3846 | 1700 | 2.2701 | 111.8156 |
74
- | 0.0018 | 69.2308 | 1800 | 2.2764 | 112.5072 |
75
- | 0.0016 | 73.0769 | 1900 | 2.2792 | 112.1614 |
76
- | 0.0017 | 76.9231 | 2000 | 2.2804 | 111.1239 |
77
 
78
 
79
  ### Framework versions
80
 
81
- - Transformers 4.42.0.dev0
82
  - Pytorch 2.3.0+cu121
83
  - Datasets 2.20.0
84
  - Tokenizers 0.19.1
 
1
  ---
 
 
 
2
  language:
3
  - ko
4
  license: apache-2.0
5
+ base_model: openai/whisper-base
6
  tags:
7
  - hf-asr-leaderboard
8
  - generated_from_trainer
9
+ datasets:
10
+ - Oyounghyun/whisper_study_data
11
  model-index:
12
  - name: study0627
13
  results: []
 
20
 
21
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the train dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.0686
24
+ - Cer: 2.4264
25
 
26
  ## Model description
27
 
 
52
 
53
  ### Training results
54
 
55
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
56
+ |:-------------:|:-------:|:----:|:---------------:|:------:|
57
+ | 0.0599 | 1.9608 | 100 | 0.1089 | 4.6347 |
58
+ | 0.01 | 3.9216 | 200 | 0.0720 | 2.4264 |
59
+ | 0.0033 | 5.8824 | 300 | 0.0682 | 3.0807 |
60
+ | 0.002 | 7.8431 | 400 | 0.0670 | 2.5627 |
61
+ | 0.0014 | 9.8039 | 500 | 0.0667 | 2.6718 |
62
+ | 0.0011 | 11.7647 | 600 | 0.0667 | 2.5082 |
63
+ | 0.0009 | 13.7255 | 700 | 0.0668 | 2.7263 |
64
+ | 0.0008 | 15.6863 | 800 | 0.0671 | 2.5082 |
65
+ | 0.0007 | 17.6471 | 900 | 0.0674 | 2.5082 |
66
+ | 0.0006 | 19.6078 | 1000 | 0.0675 | 2.6172 |
67
+ | 0.0005 | 21.5686 | 1100 | 0.0675 | 2.5082 |
68
+ | 0.0005 | 23.5294 | 1200 | 0.0676 | 2.3991 |
69
+ | 0.0005 | 25.4902 | 1300 | 0.0679 | 2.3991 |
70
+ | 0.0004 | 27.4510 | 1400 | 0.0682 | 2.4264 |
71
+ | 0.0004 | 29.4118 | 1500 | 0.0682 | 2.4264 |
72
+ | 0.0004 | 31.3725 | 1600 | 0.0684 | 2.4264 |
73
+ | 0.0003 | 33.3333 | 1700 | 0.0684 | 2.4264 |
74
+ | 0.0004 | 35.2941 | 1800 | 0.0685 | 2.4264 |
75
+ | 0.0004 | 37.2549 | 1900 | 0.0685 | 2.4264 |
76
+ | 0.0003 | 39.2157 | 2000 | 0.0686 | 2.4264 |
77
 
78
 
79
  ### Framework versions
80
 
81
+ - Transformers 4.43.0.dev0
82
  - Pytorch 2.3.0+cu121
83
  - Datasets 2.20.0
84
  - Tokenizers 0.19.1
generation_config.json CHANGED
@@ -252,5 +252,5 @@
252
  "transcribe": 50359,
253
  "translate": 50358
254
  },
255
- "transformers_version": "4.42.0.dev0"
256
  }
 
252
  "transcribe": 50359,
253
  "translate": 50358
254
  },
255
+ "transformers_version": "4.43.0.dev0"
256
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f713bdca0a89e5e92eac417744a6958d85c8124e5f8280f0cb9adb291c388f8a
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54b77ed7c460667286dfa9dd9e0147fd27415ca8d4e38518a3f5ea7be15af622
3
  size 290403936
runs/Jun28_01-14-22_8bc15a111634/events.out.tfevents.1719537268.8bc15a111634.245.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e508a836db2705cb7accf72dce9a968c5055e4ed5f2409c493d311402f8147d
3
- size 28851
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4563ca2fc8978b47f3c66d875df6e6dcaedc89ab104da89f5d9e4c363e8f3b
3
+ size 29205