Hugging Face's logo

Jpep26
/
repo_name

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Korean
whisper
hf-asr-leaderboard
Generated from Trainer
Eval Results
Model card Files Metrics Community
Jpep26 commited on
Commit
2380ec8
·
verified ·
1 Parent(s): f875630

End of training

Browse files
Files changed (2) hide show
  1. README.md +17 -17
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,30 +1,30 @@
1
  ---
2
- base_model: openai/whisper-base
3
- datasets:
4
- - Jpep26/AfterProcessing
5
  language:
6
  - ko
7
- library_name: transformers
8
  license: apache-2.0
9
- metrics:
10
- - wer
11
  tags:
12
  - hf-asr-leaderboard
13
  - generated_from_trainer
 
 
 
 
14
  model-index:
15
  - name: Test
16
  results:
17
  - task:
18
- type: automatic-speech-recognition
19
  name: Automatic Speech Recognition
 
20
  dataset:
21
  name: AfterProcessing
22
  type: Jpep26/AfterProcessing
23
  args: 'config: ko, split: valid'
24
  metrics:
25
- - type: wer
26
- value: 0.7099697885196374
27
- name: Wer
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -35,9 +35,9 @@ should probably proofread and complete it, then remove this comment. -->
35
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the AfterProcessing dataset.
36
  It achieves the following results on the evaluation set:
37
  - Loss: 0.9167
38
- - Cer: 0.8260
39
- - Wer: 0.7100
40
- - Mean: 0.7680
41
 
42
  ## Model description
43
 
@@ -70,10 +70,10 @@ The following hyperparameters were used during training:
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Mean |
72
  |:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
73
- | 2.9456 | 0.6410 | 50 | 2.6740 | 0.5793 | 0.8061 | 0.6927 |
74
- | 1.7821 | 1.2821 | 100 | 1.6827 | 0.4616 | 0.6556 | 0.5586 |
75
- | 1.2153 | 1.9231 | 150 | 1.1410 | 0.4211 | 0.6017 | 0.5114 |
76
- | 0.8637 | 2.5641 | 200 | 0.9167 | 0.8260 | 0.7100 | 0.7680 |
77
 
78
 
79
  ### Framework versions
 
1
  ---
2
+ library_name: transformers
 
 
3
  language:
4
  - ko
 
5
  license: apache-2.0
6
+ base_model: openai/whisper-base
 
7
  tags:
8
  - hf-asr-leaderboard
9
  - generated_from_trainer
10
+ datasets:
11
+ - Jpep26/AfterProcessing
12
+ metrics:
13
+ - wer
14
  model-index:
15
  - name: Test
16
  results:
17
  - task:
 
18
  name: Automatic Speech Recognition
19
+ type: automatic-speech-recognition
20
  dataset:
21
  name: AfterProcessing
22
  type: Jpep26/AfterProcessing
23
  args: 'config: ko, split: valid'
24
  metrics:
25
+ - name: Wer
26
+ type: wer
27
+ value: 0.7054380664652568
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
35
  This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on the AfterProcessing dataset.
36
  It achieves the following results on the evaluation set:
37
  - Loss: 0.9167
38
+ - Cer: 0.8486
39
+ - Wer: 0.7054
40
+ - Mean: 0.7770
41
 
42
  ## Model description
43
 
 
70
 
71
  | Training Loss | Epoch | Step | Validation Loss | Cer | Wer | Mean |
72
  |:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
73
+ | 2.9457 | 0.6410 | 50 | 2.6739 | 0.5791 | 0.8056 | 0.6923 |
74
+ | 1.7821 | 1.2821 | 100 | 1.6827 | 0.4622 | 0.6561 | 0.5592 |
75
+ | 1.2153 | 1.9231 | 150 | 1.1411 | 0.4216 | 0.6022 | 0.5119 |
76
+ | 0.8636 | 2.5641 | 200 | 0.9167 | 0.8486 | 0.7054 | 0.7770 |
77
 
78
 
79
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fdf5b0cd958fe200608cf095afbde0aefa5ae2c08becff93ca466ae902797299
3
  size 290403936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be00e4fe3a8d0e95da92da816914e17a8f53a13ed076484a00c6033734afa736
3
  size 290403936