Hugging Face's logo

Marcusxx
/
CHUNGNAM_FM_AddressesM_model

TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Model card Files Metrics Community
Marcusxx commited on
Commit
07ce4af
•
1 Parent(s): ead510e

Model save

Browse files
Files changed (3) hide show
  1. README.md +24 -29
  2. model.safetensors +1 -1
  3. runs/Nov06_14-21-26_dev4.nectarsoft/events.out.tfevents.1730870489.dev4.nectarsoft.3375829.0 +2 -2
README.md CHANGED
@@ -1,12 +1,7 @@
1
  ---
2
- base_model: openai/whisper-medium
3
- datasets:
4
- - Marcusxx/CHUNGNAM_FM_Addresses
5
- language:
6
- - ko
7
  license: apache-2.0
 
8
  tags:
9
- - hf-asr-leaderboard
10
  - generated_from_trainer
11
  model-index:
12
  - name: CHUNGNAM_FM_AddressesM_model
@@ -18,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # CHUNGNAM_FM_AddressesM_model
20
 
21
- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Marcusxx/CHUNGNAM_FM_Addresses dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0038
24
- - Cer: 0.0909
25
 
26
  ## Model description
27
 
@@ -54,26 +49,26 @@ The following hyperparameters were used during training:
54
 
55
  | Training Loss | Epoch | Step | Validation Loss | Cer |
56
  |:-------------:|:-------:|:-----:|:---------------:|:-------:|
57
- | 0.0184 | 0.6906 | 1000 | 0.0177 | 37.1099 |
58
- | 0.0102 | 1.3812 | 2000 | 0.0118 | 12.6786 |
59
- | 0.0019 | 2.0718 | 3000 | 0.0097 | 0.3414 |
60
- | 0.0037 | 2.7624 | 4000 | 0.0072 | 0.4861 |
61
- | 0.0015 | 3.4530 | 5000 | 0.0069 | 0.1818 |
62
- | 0.0012 | 4.1436 | 6000 | 0.0043 | 0.1410 |
63
- | 0.0018 | 4.8343 | 7000 | 0.0049 | 0.1967 |
64
- | 0.0004 | 5.5249 | 8000 | 0.0050 | 0.1299 |
65
- | 0.0055 | 6.2155 | 9000 | 0.0063 | 0.1800 |
66
- | 0.0014 | 6.9061 | 10000 | 0.0049 | 0.1447 |
67
- | 0.0012 | 7.5967 | 11000 | 0.0045 | 0.1021 |
68
- | 0.0002 | 8.2873 | 12000 | 0.0044 | 0.1150 |
69
- | 0.0002 | 8.9779 | 13000 | 0.0036 | 0.1076 |
70
- | 0.0001 | 9.6685 | 14000 | 0.0041 | 0.1076 |
71
- | 0.0 | 10.3591 | 15000 | 0.0036 | 0.1021 |
72
- | 0.0001 | 11.0497 | 16000 | 0.0040 | 0.0965 |
73
- | 0.0 | 11.7403 | 17000 | 0.0038 | 0.1039 |
74
- | 0.0 | 12.4309 | 18000 | 0.0038 | 0.0928 |
75
- | 0.0 | 13.1215 | 19000 | 0.0038 | 0.0909 |
76
- | 0.0 | 13.8122 | 20000 | 0.0038 | 0.0909 |
77
 
78
 
79
  ### Framework versions
 
1
  ---
 
 
 
 
 
2
  license: apache-2.0
3
+ base_model: openai/whisper-medium
4
  tags:
 
5
  - generated_from_trainer
6
  model-index:
7
  - name: CHUNGNAM_FM_AddressesM_model
 
13
 
14
  # CHUNGNAM_FM_AddressesM_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: 0.2603
19
+ - Cer: 6.2263
20
 
21
  ## Model description
22
 
 
49
 
50
  | Training Loss | Epoch | Step | Validation Loss | Cer |
51
  |:-------------:|:-------:|:-----:|:---------------:|:-------:|
52
+ | 0.1938 | 0.6906 | 1000 | 0.2020 | 5.9531 |
53
+ | 0.1554 | 1.3812 | 2000 | 0.1852 | 5.9452 |
54
+ | 0.1048 | 2.0718 | 3000 | 0.1793 | 5.8234 |
55
+ | 0.1126 | 2.7624 | 4000 | 0.1794 | 7.6374 |
56
+ | 0.0695 | 3.4530 | 5000 | 0.1922 | 6.2990 |
57
+ | 0.0382 | 4.1436 | 6000 | 0.1999 | 6.2872 |
58
+ | 0.0385 | 4.8343 | 7000 | 0.2019 | 7.5529 |
59
+ | 0.0203 | 5.5249 | 8000 | 0.2141 | 7.6944 |
60
+ | 0.0142 | 6.2155 | 9000 | 0.2211 | 6.0239 |
61
+ | 0.0129 | 6.9061 | 10000 | 0.2190 | 8.6417 |
62
+ | 0.0109 | 7.5967 | 11000 | 0.2262 | 8.0187 |
63
+ | 0.0062 | 8.2873 | 12000 | 0.2286 | 10.8626 |
64
+ | 0.0074 | 8.9779 | 13000 | 0.2323 | 7.1874 |
65
+ | 0.005 | 9.6685 | 14000 | 0.2370 | 7.7829 |
66
+ | 0.0046 | 10.3591 | 15000 | 0.2415 | 6.2243 |
67
+ | 0.0021 | 11.0497 | 16000 | 0.2459 | 6.0946 |
68
+ | 0.002 | 11.7403 | 17000 | 0.2474 | 6.1713 |
69
+ | 0.0009 | 12.4309 | 18000 | 0.2572 | 6.0887 |
70
+ | 0.0001 | 13.1215 | 19000 | 0.2582 | 6.2715 |
71
+ | 0.0002 | 13.8122 | 20000 | 0.2603 | 6.2263 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3d06750ef5e4f8f870475d5cc2dfc21e5252a8f34f0d4ff5563b2f4e28cf273
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32017813211f1c2d17ca5b44b9a0902515474e7e7d01ff9ae35364742b499272
3
  size 3055544304
runs/Nov06_14-21-26_dev4.nectarsoft/events.out.tfevents.1730870489.dev4.nectarsoft.3375829.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e0e4e8530b8ff042bd6053c73553ec52816a81b384ef93ed625b3d45e269d4d
3
- size 181423
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b05094c57613ebe17907eaa2e14372376d9d7dfa26c93aef1ffa4e38426eac1d
3
+ size 181783