Hugging Face's logo

Marcusxx
/
CngFSt3T_small_model

TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Model card Files Metrics Community
Marcusxx commited on
Commit
29baf9f
·
verified ·
1 Parent(s): 38b1cbf

Model save

Browse files
Files changed (3) hide show
  1. README.md +10 -15
  2. model.safetensors +1 -1
  3. runs/Dec12_12-53-27_localhost.localdomain/events.out.tfevents.1733975610.localhost.localdomain.327.0 +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-small
9
- datasets:
10
- - Marcusxx/CngFSt3T
11
  model-index:
12
  - name: CngFSt3T_small_model
13
  results: []
@@ -18,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # CngFSt3T_small_model
20
 
21
- This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Marcusxx/CngFSt3T dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0723
24
- - Cer: 135.0080
25
 
26
  ## Model description
27
 
@@ -40,7 +35,7 @@ More information needed
40
  ### Training hyperparameters
41
 
42
  The following hyperparameters were used during training:
43
- - learning_rate: 1e-05
44
  - train_batch_size: 16
45
  - eval_batch_size: 8
46
  - seed: 42
@@ -54,11 +49,11 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Cer |
56
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
57
- | 0.0452 | 2.2321 | 1000 | 0.1419 | 74.5039 |
58
- | 0.0061 | 4.4643 | 2000 | 0.0770 | 130.8381 |
59
- | 0.0006 | 6.6964 | 3000 | 0.0710 | 118.6804 |
60
- | 0.0003 | 8.9286 | 4000 | 0.0722 | 121.9459 |
61
- | 0.0003 | 11.1607 | 5000 | 0.0723 | 135.0080 |
62
 
63
 
64
  ### Framework versions
 
1
  ---
 
 
2
  license: apache-2.0
3
+ base_model: openai/whisper-small
4
  tags:
 
5
  - generated_from_trainer
 
 
 
6
  model-index:
7
  - name: CngFSt3T_small_model
8
  results: []
 
13
 
14
  # CngFSt3T_small_model
15
 
16
+ This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.1722
19
+ - Cer: 158.1261
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 1e-06
39
  - train_batch_size: 16
40
  - eval_batch_size: 8
41
  - seed: 42
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Cer |
51
  |:-------------:|:-------:|:----:|:---------------:|:--------:|
52
+ | 0.4693 | 2.2321 | 1000 | 0.5347 | 45.6669 |
53
+ | 0.2295 | 4.4643 | 2000 | 0.3416 | 101.5993 |
54
+ | 0.1157 | 6.6964 | 3000 | 0.2390 | 136.4398 |
55
+ | 0.071 | 8.9286 | 4000 | 0.1865 | 134.9996 |
56
+ | 0.0579 | 11.1607 | 5000 | 0.1722 | 158.1261 |
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:596aa84fb254fd728bd8408c51b7408f2709bbe3931713a9c343e6bf405ab9d0
3
  size 966995080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e8ac7056ec073f84b8e2c10d9e984715deb51211c6f7c2607caeae53f9eb788
3
  size 966995080
runs/Dec12_12-53-27_localhost.localdomain/events.out.tfevents.1733975610.localhost.localdomain.327.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0038389322c357b415b77697627af166cca4c8e8c0b0235569608b0271c788ea
3
- size 49428
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf816604cc541e433562e667c8bca4ae3cfb7b7be9acce0c85a68256c0b9aef
3
+ size 49782