Hugging Face's logo

kotoba-tech
/
kotoba-whisper-v1.1

Automatic Speech Recognition
Transformers
Safetensors
Japanese
whisper
audio
hf-asr-leaderboard
Model card Files Community
1
asahi417 commited on
Commit
7dd6751
·
verified ·
1 Parent(s): 1b7749a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -29,10 +29,10 @@ model-index:
29
  metrics:
30
  - name: WER
31
  type: WER
32
- value: TBA
33
  - name: CER
34
  type: CER
35
- value: TBA
36
  - task:
37
  type: automatic-speech-recognition
38
  dataset:
@@ -41,10 +41,10 @@ model-index:
41
  metrics:
42
  - name: WER
43
  type: WER
44
- value: TBA
45
  - name: CER
46
  type: CER
47
- value: TBA
48
  - task:
49
  type: automatic-speech-recognition
50
  dataset:
@@ -53,10 +53,10 @@ model-index:
53
  metrics:
54
  - name: WER
55
  type: WER
56
- value: TBA
57
  - name: CER
58
  type: CER
59
- value: TBA
60
  ---
61
 
62
  # Kotoba-Whisper-v1.1
 
29
  metrics:
30
  - name: WER
31
  type: WER
32
+ value: 59.27
33
  - name: CER
34
  type: CER
35
+ value: 9.44
36
  - task:
37
  type: automatic-speech-recognition
38
  dataset:
 
41
  metrics:
42
  - name: WER
43
  type: WER
44
+ value: 56.62
45
  - name: CER
46
  type: CER
47
+ value: 12.60
48
  - task:
49
  type: automatic-speech-recognition
50
  dataset:
 
53
  metrics:
54
  - name: WER
55
  type: WER
56
+ value: 64.36
57
  - name: CER
58
  type: CER
59
+ value: 8.48
60
  ---
61
 
62
  # Kotoba-Whisper-v1.1