Hugging Face's logo

comodoro
/
wav2vec2-xls-r-300m-sr-cv8

Automatic Speech Recognition Transformers PyTorch Serbian wav2vec2 mozilla-foundation/common_voice_8_0 generated_from_trainer robust-speech-event xlsr-fine-tuning-week hf-asr-leaderboard Eval Results Inference Endpoints
Model card Files Community
anton-l HF staff commited on
Commit
b845074
•
1 Parent(s): 8a3436e

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -7
README.md CHANGED
@@ -13,19 +13,55 @@ datasets:
13
  - name: Serbian comodoro Wav2Vec2 XLSR 300M CV8
14
  results:
15
  - task:
16
- name: Automatic Speech Recognition
17
  type: automatic-speech-recognition
18
  dataset:
19
  name: Common Voice 8
20
  type: mozilla-foundation/common_voice_8_0
21
  args: sr
22
  metrics:
23
- - name: Test WER
24
- type: wer
25
- value: 48.5
26
- - name: Test CER
27
- type: cer
28
- value: 18.4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29
  ---
30
 
31
  # Serbian wav2vec2-xls-r-300m-sr-cv8
13
  - name: Serbian comodoro Wav2Vec2 XLSR 300M CV8
14
  results:
15
  - task:
16
+ name: Automatic Speech Recognition
17
  type: automatic-speech-recognition
18
  dataset:
19
  name: Common Voice 8
20
  type: mozilla-foundation/common_voice_8_0
21
  args: sr
22
  metrics:
23
+ - name: Test WER
24
+ type: wer
25
+ value: 48.5
26
+ - name: Test CER
27
+ type: cer
28
+ value: 18.4
29
+ model-index:
30
+ - name: wav2vec2-xls-r-300m-sr-cv8
31
+ results:
32
+ - task:
33
+ name: Automatic Speech Recognition
34
+ type: automatic-speech-recognition
35
+ dataset:
36
+ name: Common Voice 8.0
37
+ type: mozilla-foundation/common_voice_8_0
38
+ args: sr
39
+ metrics:
40
+ - name: Test WER
41
+ type: wer
42
+ value: 48.53
43
+ - task:
44
+ name: Automatic Speech Recognition
45
+ type: automatic-speech-recognition
46
+ dataset:
47
+ name: Robust Speech Event - Dev Data
48
+ type: speech-recognition-community-v2/dev_data
49
+ args: sr
50
+ metrics:
51
+ - name: Test WER
52
+ type: wer
53
+ value: 97.43
54
+ - task:
55
+ name: Automatic Speech Recognition
56
+ type: automatic-speech-recognition
57
+ dataset:
58
+ name: Robust Speech Event - Test Data
59
+ type: speech-recognition-community-v2/eval_data
60
+ args: sr
61
+ metrics:
62
+ - name: Test WER
63
+ type: wer
64
+ value: 96.69
65
  ---
66
 
67
  # Serbian wav2vec2-xls-r-300m-sr-cv8