Hugging Face's logo

Marcusxx
/
cheonanAddresses_torchmodel_model

TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Model card Files Metrics Community
Marcusxx commited on
Commit
3e193f2
·
verified ·
1 Parent(s): 1dda466

Model save

Browse files
Files changed (3) hide show
  1. README.md +15 -20
  2. model.safetensors +1 -1
  3. runs/Oct18_16-09-19_dev4.nectarsoft/events.out.tfevents.1729235360.dev4.nectarsoft.1263889.0 +2 -2
README.md CHANGED
@@ -1,13 +1,8 @@
1
  ---
2
- language:
3
- - ko
4
  license: apache-2.0
 
5
  tags:
6
- - hf-asr-leaderboard
7
  - generated_from_trainer
8
- base_model: openai/whisper-medium
9
- datasets:
10
- - Marcusxx/cheonanAddresses
11
  model-index:
12
  - name: cheonanAddresses_torchmodel_model
13
  results: []
@@ -18,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # cheonanAddresses_torchmodel_model
20
 
21
- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Marcusxx/cheonanAddresses dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0531
24
- - Cer: 14.2607
25
 
26
  ## Model description
27
 
@@ -54,21 +49,21 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Cer |
56
  |:-------------:|:------:|:-----:|:---------------:|:-------:|
57
- | 0.0765 | 0.3101 | 1000 | 0.0767 | 27.7467 |
58
- | 0.0698 | 0.6202 | 2000 | 0.0717 | 2.6100 |
59
- | 0.0624 | 0.9302 | 3000 | 0.0667 | 3.7811 |
60
- | 0.0597 | 1.2403 | 4000 | 0.0629 | 2.1665 |
61
- | 0.0598 | 1.5504 | 5000 | 0.0602 | 2.0783 |
62
- | 0.0557 | 1.8605 | 6000 | 0.0586 | 5.0203 |
63
- | 0.0512 | 2.1705 | 7000 | 0.0566 | 16.9546 |
64
- | 0.0441 | 2.4806 | 8000 | 0.0558 | 13.6386 |
65
- | 0.0533 | 2.7907 | 9000 | 0.0537 | 13.8057 |
66
- | 0.0376 | 3.1008 | 10000 | 0.0531 | 14.2607 |
67
 
68
 
69
  ### Framework versions
70
 
71
  - Transformers 4.41.2
72
  - Pytorch 2.2.2+cu121
73
- - Datasets 2.19.2
74
  - Tokenizers 0.19.1
 
1
  ---
 
 
2
  license: apache-2.0
3
+ base_model: openai/whisper-medium
4
  tags:
 
5
  - generated_from_trainer
 
 
 
6
  model-index:
7
  - name: cheonanAddresses_torchmodel_model
8
  results: []
 
13
 
14
  # cheonanAddresses_torchmodel_model
15
 
16
+ This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.0528
19
+ - Cer: 1.9329
20
 
21
  ## Model description
22
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Cer |
51
  |:-------------:|:------:|:-----:|:---------------:|:-------:|
52
+ | 0.0767 | 0.3101 | 1000 | 0.0752 | 36.5220 |
53
+ | 0.0692 | 0.6202 | 2000 | 0.0718 | 2.2982 |
54
+ | 0.0619 | 0.9302 | 3000 | 0.0674 | 2.2475 |
55
+ | 0.0579 | 1.2403 | 4000 | 0.0637 | 2.1839 |
56
+ | 0.0605 | 1.5504 | 5000 | 0.0630 | 2.1412 |
57
+ | 0.0549 | 1.8605 | 6000 | 0.0591 | 2.1101 |
58
+ | 0.0502 | 2.1705 | 7000 | 0.0566 | 2.0081 |
59
+ | 0.0436 | 2.4806 | 8000 | 0.0558 | 2.0168 |
60
+ | 0.0518 | 2.7907 | 9000 | 0.0536 | 1.9705 |
61
+ | 0.037 | 3.1008 | 10000 | 0.0528 | 1.9329 |
62
 
63
 
64
  ### Framework versions
65
 
66
  - Transformers 4.41.2
67
  - Pytorch 2.2.2+cu121
68
+ - Datasets 2.20.0
69
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ab1dc2aa64dc6540b032ce54d6415d95feb1ff6911297ca5939bac1fcd48e04
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37efbb19785629beb4b3a3b809cc8f76003ac7fbdac4155dd54f78e559259bf0
3
  size 3055544304
runs/Oct18_16-09-19_dev4.nectarsoft/events.out.tfevents.1729235360.dev4.nectarsoft.1263889.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06ba7bf57d858a0eba8924aa66c77c6c85b405f216e631fdba45b60d6efee9c7
3
- size 84496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c19b92e9dae9d31ef9b4d7f8a9d4ebb7fa7f49440c104841da08cee5c331432
3
+ size 93608