Hugging Face's logo

Marcusxx
/
CngFSt3T_model

TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Model card Files Metrics Community
Marcusxx commited on
Commit
ee3c319
·
verified ·
1 Parent(s): 259f277

Model save

Browse files
Files changed (3) hide show
  1. README.md +12 -15
  2. model.safetensors +1 -1
  3. runs/Dec05_14-19-03_dev4.nectarsoft/events.out.tfevents.1733375944.dev4.nectarsoft.2196704.0 +2 -2
README.md CHANGED
@@ -1,12 +1,7 @@
1
  ---
2
- base_model: openai/whisper-medium
3
- datasets:
4
- - Marcusxx/CngFSt3T
5
- language:
6
- - ko
7
  license: apache-2.0
 
8
  tags:
9
- - hf-asr-leaderboard
10
  - generated_from_trainer
11
  model-index:
12
  - name: CngFSt3T_model
@@ -18,10 +13,10 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  # CngFSt3T_model
20
 
21
- This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Marcusxx/CngFSt3T dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 0.0722
24
- - Cer: 13.0034
25
 
26
  ## Model description
27
 
@@ -47,16 +42,18 @@ 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: 250
50
- - training_steps: 3000
51
  - mixed_precision_training: Native AMP
52
 
53
  ### Training results
54
 
55
- | Training Loss | Epoch | Step | Validation Loss | Cer |
56
- |:-------------:|:------:|:----:|:---------------:|:-------:|
57
- | 0.0378 | 2.2321 | 1000 | 0.1281 | 23.0679 |
58
- | 0.0012 | 4.4643 | 2000 | 0.0755 | 17.4412 |
59
- | 0.0004 | 6.6964 | 3000 | 0.0722 | 13.0034 |
 
 
60
 
61
 
62
  ### 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: CngFSt3T_model
 
13
 
14
  # CngFSt3T_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: 0.0744
19
+ - Cer: 6.6985
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: 250
45
+ - training_steps: 5000
46
  - mixed_precision_training: Native AMP
47
 
48
  ### Training results
49
 
50
+ | Training Loss | Epoch | Step | Validation Loss | Cer |
51
+ |:-------------:|:-------:|:----:|:---------------:|:-------:|
52
+ | 0.0455 | 2.2321 | 1000 | 0.1281 | 22.1217 |
53
+ | 0.0061 | 4.4643 | 2000 | 0.0814 | 22.4315 |
54
+ | 0.0008 | 6.6964 | 3000 | 0.0802 | 5.5849 |
55
+ | 0.0003 | 8.9286 | 4000 | 0.0747 | 6.6650 |
56
+ | 0.0001 | 11.1607 | 5000 | 0.0744 | 6.6985 |
57
 
58
 
59
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb9831f0367c309bba425c8edc4839bec28084244fd565cc099465d82ce185ce
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d26ed636d65d6b1e8dd68289b3e2f5268f49296c326d81e745d20e22ae302f3
3
  size 3055544304
runs/Dec05_14-19-03_dev4.nectarsoft/events.out.tfevents.1733375944.dev4.nectarsoft.2196704.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c248b0d067eb4e6d493a79027a9ff7bd1982c10907c61c1c9930bc9d4a41823e
3
- size 49406
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b8cfb7fbc81d074a50445e2814cda602fae5211e67ddcc546294e78917e7f05
3
+ size 49760