Hugging Face's logo

jonatasgrosman
/
wav2vec2-large-xlsr-53-portuguese

Automatic Speech Recognition
Transformers
PyTorch
JAX
Portuguese
wav2vec2
audio
hf-asr-leaderboard
mozilla-foundation/common_voice_6_0
robust-speech-event
speech
xlsr-fine-tuning-week
Eval Results
Inference Endpoints
Model card Files Community
2
anton-l HF staff commited on
Commit
f4fbf4a
•
1 Parent(s): e449ab9

Upload README.md

Browse files
Files changed (1) hide show
  1. README.md +28 -27
README.md CHANGED
@@ -15,30 +15,31 @@ tags:
15
  - xlsr-fine-tuning-week
16
  - robust-speech-event
17
  - mozilla-foundation/common_voice_6_0
 
18
  model-index:
19
  - name: XLSR Wav2Vec2 Portuguese by Jonatas Grosman
20
  results:
21
- - task:
22
- name: Automatic Speech Recognition
23
  type: automatic-speech-recognition
24
  dataset:
25
  name: Common Voice pt
26
  type: common_voice
27
  args: pt
28
  metrics:
29
- - name: Test WER
30
- type: wer
31
- value: 11.31
32
- - name: Test CER
33
- type: cer
34
- value: 3.74
35
- - name: Test WER (+LM)
36
- type: wer
37
- value: 9.01
38
- - name: Test CER (+LM)
39
- type: cer
40
- value: 3.21
41
- - task:
42
  name: Automatic Speech Recognition
43
  type: automatic-speech-recognition
44
  dataset:
@@ -46,18 +47,18 @@ model-index:
46
  type: speech-recognition-community-v2/dev_data
47
  args: pt
48
  metrics:
49
- - name: Dev WER
50
- type: wer
51
- value: 42.10
52
- - name: Dev CER
53
- type: cer
54
- value: 17.93
55
- - name: Dev WER (+LM)
56
- type: wer
57
- value: 36.92
58
- - name: Dev CER (+LM)
59
- type: cer
60
- value: 16.88
61
  ---
62
 
63
  # Wav2Vec2-Large-XLSR-53-Portuguese
 
15
  - xlsr-fine-tuning-week
16
  - robust-speech-event
17
  - mozilla-foundation/common_voice_6_0
18
+ - hf-asr-leaderboard
19
  model-index:
20
  - name: XLSR Wav2Vec2 Portuguese by Jonatas Grosman
21
  results:
22
+ - task:
23
+ name: Automatic Speech Recognition
24
  type: automatic-speech-recognition
25
  dataset:
26
  name: Common Voice pt
27
  type: common_voice
28
  args: pt
29
  metrics:
30
+ - name: Test WER
31
+ type: wer
32
+ value: 11.31
33
+ - name: Test CER
34
+ type: cer
35
+ value: 3.74
36
+ - name: Test WER (+LM)
37
+ type: wer
38
+ value: 9.01
39
+ - name: Test CER (+LM)
40
+ type: cer
41
+ value: 3.21
42
+ - task:
43
  name: Automatic Speech Recognition
44
  type: automatic-speech-recognition
45
  dataset:
 
47
  type: speech-recognition-community-v2/dev_data
48
  args: pt
49
  metrics:
50
+ - name: Dev WER
51
+ type: wer
52
+ value: 42.1
53
+ - name: Dev CER
54
+ type: cer
55
+ value: 17.93
56
+ - name: Dev WER (+LM)
57
+ type: wer
58
+ value: 36.92
59
+ - name: Dev CER (+LM)
60
+ type: cer
61
+ value: 16.88
62
  ---
63
 
64
  # Wav2Vec2-Large-XLSR-53-Portuguese