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
d796f7e
•
1 Parent(s): 4a559c7

End of training

Browse files
Files changed (3) hide show
  1. README.md +25 -55
  2. model.safetensors +1 -1
  3. runs/Jun27_00-02-33_2fe4694086de/events.out.tfevents.1719446562.2fe4694086de.1424.0 +2 -2
README.md CHANGED
@@ -9,19 +9,19 @@ tags:
9
  datasets:
10
  - Oyounghyun/whisper_study_data
11
  model-index:
12
- - name: study0625
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # study0625
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: 2.0936
24
- - Cer: 153.8515
25
 
26
  ## Model description
27
 
@@ -47,63 +47,33 @@ The following hyperparameters were used during training:
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 10
50
- - training_steps: 1000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Cer |
56
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
- | No log | 0.9524 | 20 | 3.5635 | 646.1485 |
58
- | 4.3375 | 1.9048 | 40 | 2.7999 | 742.0541 |
59
- | 2.5651 | 2.8571 | 60 | 2.4367 | 707.9806 |
60
- | 1.9869 | 3.8095 | 80 | 2.2307 | 717.5573 |
61
- | 1.6234 | 4.7619 | 100 | 2.0978 | 730.5344 |
62
- | 1.6234 | 5.7143 | 120 | 1.9981 | 219.3616 |
63
- | 1.3356 | 6.6667 | 140 | 1.9375 | 308.4663 |
64
- | 1.1087 | 7.6190 | 160 | 1.8929 | 240.8050 |
65
- | 0.9213 | 8.5714 | 180 | 1.8348 | 132.8938 |
66
- | 0.804 | 9.5238 | 200 | 1.8248 | 126.4400 |
67
- | 0.804 | 10.4762 | 220 | 1.7858 | 108.2582 |
68
- | 0.6823 | 11.4286 | 240 | 1.7983 | 165.4407 |
69
- | 0.5797 | 12.3810 | 260 | 1.7943 | 191.1867 |
70
- | 0.4921 | 13.3333 | 280 | 1.7901 | 139.6253 |
71
- | 0.4159 | 14.2857 | 300 | 1.7978 | 180.4997 |
72
- | 0.4159 | 15.2381 | 320 | 1.8185 | 131.2283 |
73
- | 0.3513 | 16.1905 | 340 | 1.8199 | 141.4296 |
74
- | 0.2958 | 17.1429 | 360 | 1.8410 | 187.4393 |
75
- | 0.2438 | 18.0952 | 380 | 1.8407 | 219.3616 |
76
- | 0.2135 | 19.0476 | 400 | 1.8424 | 162.0402 |
77
- | 0.2135 | 20.0 | 420 | 1.8452 | 183.4837 |
78
- | 0.1676 | 20.9524 | 440 | 1.8615 | 172.4497 |
79
- | 0.1509 | 21.9048 | 460 | 1.8842 | 132.8244 |
80
- | 0.1208 | 22.8571 | 480 | 1.8908 | 179.9445 |
81
- | 0.1001 | 23.8095 | 500 | 1.9055 | 180.7772 |
82
- | 0.1001 | 24.7619 | 520 | 1.9258 | 131.0895 |
83
- | 0.0805 | 25.7143 | 540 | 1.9154 | 136.1554 |
84
- | 0.063 | 26.6667 | 560 | 1.9319 | 178.5566 |
85
- | 0.0513 | 27.6190 | 580 | 1.9731 | 162.3178 |
86
- | 0.0452 | 28.5714 | 600 | 1.9633 | 175.0867 |
87
- | 0.0452 | 29.5238 | 620 | 1.9614 | 167.2450 |
88
- | 0.0374 | 30.4762 | 640 | 1.9872 | 178.5566 |
89
- | 0.0298 | 31.4286 | 660 | 1.9845 | 169.8126 |
90
- | 0.0241 | 32.3810 | 680 | 2.0082 | 138.0985 |
91
- | 0.0195 | 33.3333 | 700 | 2.0180 | 148.5080 |
92
- | 0.0195 | 34.2857 | 720 | 2.0217 | 165.5795 |
93
- | 0.0162 | 35.2381 | 740 | 2.0419 | 147.3282 |
94
- | 0.0136 | 36.1905 | 760 | 2.0427 | 124.9133 |
95
- | 0.0111 | 37.1429 | 780 | 2.0552 | 147.0507 |
96
- | 0.0097 | 38.0952 | 800 | 2.0653 | 154.7536 |
97
- | 0.0097 | 39.0476 | 820 | 2.0683 | 145.1770 |
98
- | 0.0083 | 40.0 | 840 | 2.0769 | 159.3338 |
99
- | 0.008 | 40.9524 | 860 | 2.0790 | 147.8834 |
100
- | 0.007 | 41.9048 | 880 | 2.0818 | 153.5739 |
101
- | 0.007 | 42.8571 | 900 | 2.0863 | 158.7092 |
102
- | 0.007 | 43.8095 | 920 | 2.0896 | 151.6308 |
103
- | 0.0065 | 44.7619 | 940 | 2.0923 | 159.8890 |
104
- | 0.0064 | 45.7143 | 960 | 2.0928 | 150.3123 |
105
- | 0.006 | 46.6667 | 980 | 2.0934 | 159.7502 |
106
- | 0.006 | 47.6190 | 1000 | 2.0936 | 153.8515 |
107
 
108
 
109
  ### Framework versions
 
9
  datasets:
10
  - Oyounghyun/whisper_study_data
11
  model-index:
12
+ - name: study0627
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # study0627
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
 
 
47
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
48
  - lr_scheduler_type: linear
49
  - lr_scheduler_warmup_steps: 10
50
+ - training_steps: 2000
51
  - mixed_precision_training: Native AMP
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
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9849784add807d33a6b4bb43acd6812efcdb0a9e5ac9f066559980c333390704
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7048669d3c059d44465ff1512415b37a2611ea36be3757e0d425de91d0d56ff9
3
  size 290403936
runs/Jun27_00-02-33_2fe4694086de/events.out.tfevents.1719446562.2fe4694086de.1424.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:994d6a59daacce266c1fb32befa5491adfcd23a33c3921d0fa5e396c6133518c
3
- size 27689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b0adff6e305d2b7b8463085365db67b7f45b8a9dafe60ad5c4e119deaba543b
3
+ size 29205