alkiskoudounas librarian-bot commited on
Commit
4dcfe12
1 Parent(s): 2ec7d20

Librarian Bot: Add base_model information to model (#1)

Browse files

- Librarian Bot: Add base_model information to model (9b646fb01f22465d3107a7636e21acdeb7a77e30)


Co-authored-by: Librarian Bot (Bot) <librarian-bot@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +23 -22
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
- license: apache-2.0
3
  language: it
 
4
  tags:
5
  - automatic-speech-recognition
6
  - generated_from_trainer
@@ -8,60 +8,61 @@ tags:
8
  - robust-speech-event
9
  datasets:
10
  - mozilla-foundation/common_voice_7_0
 
11
  model-index:
12
  - name: XLS-R-300m - Italian
13
  results:
14
  - task:
15
- name: Automatic Speech Recognition
16
  type: automatic-speech-recognition
 
17
  dataset:
18
  name: Common Voice 7
19
  type: mozilla-foundation/common_voice_7_0
20
  args: it
21
  metrics:
22
- - name: Test WER
23
- type: wer
24
  value: 17.17
25
- - name: Test CER
26
- type: cer
27
  value: 4.27
28
- - name: Test WER (+LM)
29
- type: wer
30
  value: 12.07
31
- - name: Test CER (+LM)
32
- type: cer
33
  value: 3.52
 
34
  - task:
35
- name: Automatic Speech Recognition
36
  type: automatic-speech-recognition
 
37
  dataset:
38
  name: Robust Speech Event - Dev Data
39
  type: speech-recognition-community-v2/dev_data
40
  args: it
41
  metrics:
42
- - name: Test WER
43
- type: wer
44
  value: 24.29
45
- - name: Test CER
46
- type: cer
47
  value: 8.1
48
- - name: Test WER (+LM)
49
- type: wer
50
  value: 17.36
51
- - name: Test CER (+LM)
52
- type: cer
53
  value: 7.94
 
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: it
61
  metrics:
62
- - name: Test WER
63
- type: wer
64
  value: 33.66
 
65
  ---
66
 
67
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
1
  ---
 
2
  language: it
3
+ license: apache-2.0
4
  tags:
5
  - automatic-speech-recognition
6
  - generated_from_trainer
 
8
  - robust-speech-event
9
  datasets:
10
  - mozilla-foundation/common_voice_7_0
11
+ base_model: facebook/wav2vec2-xls-r-300m
12
  model-index:
13
  - name: XLS-R-300m - Italian
14
  results:
15
  - task:
 
16
  type: automatic-speech-recognition
17
+ name: Automatic Speech Recognition
18
  dataset:
19
  name: Common Voice 7
20
  type: mozilla-foundation/common_voice_7_0
21
  args: it
22
  metrics:
23
+ - type: wer
 
24
  value: 17.17
25
+ name: Test WER
26
+ - type: cer
27
  value: 4.27
28
+ name: Test CER
29
+ - type: wer
30
  value: 12.07
31
+ name: Test WER (+LM)
32
+ - type: cer
33
  value: 3.52
34
+ name: Test CER (+LM)
35
  - task:
 
36
  type: automatic-speech-recognition
37
+ name: Automatic Speech Recognition
38
  dataset:
39
  name: Robust Speech Event - Dev Data
40
  type: speech-recognition-community-v2/dev_data
41
  args: it
42
  metrics:
43
+ - type: wer
 
44
  value: 24.29
45
+ name: Test WER
46
+ - type: cer
47
  value: 8.1
48
+ name: Test CER
49
+ - type: wer
50
  value: 17.36
51
+ name: Test WER (+LM)
52
+ - type: cer
53
  value: 7.94
54
+ name: Test CER (+LM)
55
  - task:
 
56
  type: automatic-speech-recognition
57
+ name: Automatic Speech Recognition
58
  dataset:
59
  name: Robust Speech Event - Test Data
60
  type: speech-recognition-community-v2/eval_data
61
  args: it
62
  metrics:
63
+ - type: wer
 
64
  value: 33.66
65
+ name: Test WER
66
  ---
67
 
68
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You