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
9574549
•
1 Parent(s): 4ecf21e

Model save

Browse files
Files changed (3) hide show
  1. README.md +27 -22
  2. model.safetensors +1 -1
  3. runs/Oct28_10-30-11_dev4.nectarsoft/events.out.tfevents.1730079013.dev4.nectarsoft.2428471.0 +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: 0.0028
24
- - Cer: 0.3136
25
 
26
  ## Model description
27
 
@@ -47,23 +42,33 @@ 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: 100
50
- - training_steps: 10000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Cer |
56
- |:-------------:|:------:|:-----:|:---------------:|:-------:|
57
- | 0.0183 | 0.6906 | 1000 | 0.0229 | 12.0681 |
58
- | 0.0122 | 1.3812 | 2000 | 0.0123 | 6.4812 |
59
- | 0.001 | 2.0718 | 3000 | 0.0069 | 1.0985 |
60
- | 0.0024 | 2.7624 | 4000 | 0.0048 | 0.6624 |
61
- | 0.0022 | 3.4530 | 5000 | 0.0053 | 0.1633 |
62
- | 0.0011 | 4.1436 | 6000 | 0.0033 | 0.0983 |
63
- | 0.0002 | 4.8343 | 7000 | 0.0029 | 2.2785 |
64
- | 0.0002 | 5.5249 | 8000 | 0.0029 | 0.8869 |
65
- | 0.0 | 6.2155 | 9000 | 0.0033 | 0.3470 |
66
- | 0.0 | 6.9061 | 10000 | 0.0028 | 0.3136 |
 
 
 
 
 
 
 
 
 
 
67
 
68
 
69
  ### 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: 0.0038
19
+ - Cer: 0.0909
20
 
21
  ## Model description
22
 
 
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
  - lr_scheduler_warmup_steps: 100
45
+ - training_steps: 20000
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
51
+ |:-------------:|:-------:|:-----:|:---------------:|:-------:|
52
+ | 0.0184 | 0.6906 | 1000 | 0.0177 | 37.1099 |
53
+ | 0.0102 | 1.3812 | 2000 | 0.0118 | 12.6786 |
54
+ | 0.0019 | 2.0718 | 3000 | 0.0097 | 0.3414 |
55
+ | 0.0037 | 2.7624 | 4000 | 0.0072 | 0.4861 |
56
+ | 0.0015 | 3.4530 | 5000 | 0.0069 | 0.1818 |
57
+ | 0.0012 | 4.1436 | 6000 | 0.0043 | 0.1410 |
58
+ | 0.0018 | 4.8343 | 7000 | 0.0049 | 0.1967 |
59
+ | 0.0004 | 5.5249 | 8000 | 0.0050 | 0.1299 |
60
+ | 0.0055 | 6.2155 | 9000 | 0.0063 | 0.1800 |
61
+ | 0.0014 | 6.9061 | 10000 | 0.0049 | 0.1447 |
62
+ | 0.0012 | 7.5967 | 11000 | 0.0045 | 0.1021 |
63
+ | 0.0002 | 8.2873 | 12000 | 0.0044 | 0.1150 |
64
+ | 0.0002 | 8.9779 | 13000 | 0.0036 | 0.1076 |
65
+ | 0.0001 | 9.6685 | 14000 | 0.0041 | 0.1076 |
66
+ | 0.0 | 10.3591 | 15000 | 0.0036 | 0.1021 |
67
+ | 0.0001 | 11.0497 | 16000 | 0.0040 | 0.0965 |
68
+ | 0.0 | 11.7403 | 17000 | 0.0038 | 0.1039 |
69
+ | 0.0 | 12.4309 | 18000 | 0.0038 | 0.0928 |
70
+ | 0.0 | 13.1215 | 19000 | 0.0038 | 0.0909 |
71
+ | 0.0 | 13.8122 | 20000 | 0.0038 | 0.0909 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eeff4edb143d90601f3cbc522d3a7ee7237ac58b3442a2b6db1b0544a1565a44
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ef892e351b05b9099aa7dfdf88ab632d68d1c187ac65e47c46ed5013527348c
3
  size 3055544304
runs/Oct28_10-30-11_dev4.nectarsoft/events.out.tfevents.1730079013.dev4.nectarsoft.2428471.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e858060380e98a4657f8870f83980124ffb9ac00a02257ef1cce6a32d808ad0a
3
- size 181423
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf972e6e0e1fed553451484d7cafb2abe38485a6da7f4f5fc1b7163382b1e75d
3
+ size 181783