Hugging Face's logo

Jzuluaga
/
wav2vec2-large-960h-lv60-self-en-atc-uwb-atcc

Automatic Speech Recognition
Transformers
PyTorch
English
wav2vec2
audio
en-atc
generated_from_trainer
Eval Results
Inference Endpoints
Model card Files Community
1
Jzuluaga librarian-bot commited on
Commit
3f0dd74
•
1 Parent(s): 232864d

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

Browse files

- Librarian Bot: Add base_model information to model (579475d02d65d8ba07582763dbb77526de21b224)


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

Files changed (1) hide show
  1. README.md +21 -20
README.md CHANGED
@@ -1,53 +1,54 @@
1
  ---
2
- license: apache-2.0
3
  language: en
4
- datasets:
5
- - Jzuluaga/uwb_atcc
6
  tags:
7
  - audio
8
  - automatic-speech-recognition
9
  - en-atc
10
  - en
11
  - generated_from_trainer
 
 
12
  metrics:
13
  - wer
 
14
  model-index:
15
  - name: wav2vec2-large-960h-lv60-self-en-atc-uwb-atcc
16
  results:
17
  - task:
18
- type: automatic-speech-recognition
19
- name: Speech Recognition
20
  dataset:
21
- type: Jzuluaga/uwb_atcc
22
- name: UWB-ATCC dataset (Air Traffic Control Communications)
23
- config: test
24
- split: test
25
  metrics:
26
  - type: wer
27
- value: 17.20
28
  name: TEST WER
29
- verified: False
30
  - type: wer
31
  value: 13.72
32
  name: TEST WER (+LM)
33
- verified: False
34
  - task:
35
- type: automatic-speech-recognition
36
- name: Speech Recognition
37
  dataset:
38
- type: Jzuluaga/atcosim_corpus
39
- name: ATCOSIM corpus (Air Traffic Control Communications)
40
- config: test
41
- split: test
42
  metrics:
43
  - type: wer
44
  value: 15.31
45
  name: TEST WER
46
- verified: False
47
  - type: wer
48
  value: 11.88
49
  name: TEST WER (+LM)
50
- verified: False
51
  ---
52
 
53
  # wav2vec2-large-960h-lv60-self-en-atc-uwb-atcc
 
1
  ---
 
2
  language: en
3
+ license: apache-2.0
 
4
  tags:
5
  - audio
6
  - automatic-speech-recognition
7
  - en-atc
8
  - en
9
  - generated_from_trainer
10
+ datasets:
11
+ - Jzuluaga/uwb_atcc
12
  metrics:
13
  - wer
14
+ base_model: facebook/wav2vec2-large-960h-lv60-self
15
  model-index:
16
  - name: wav2vec2-large-960h-lv60-self-en-atc-uwb-atcc
17
  results:
18
  - task:
19
+ type: automatic-speech-recognition
20
+ name: Speech Recognition
21
  dataset:
22
+ name: UWB-ATCC dataset (Air Traffic Control Communications)
23
+ type: Jzuluaga/uwb_atcc
24
+ config: test
25
+ split: test
26
  metrics:
27
  - type: wer
28
+ value: 17.2
29
  name: TEST WER
30
+ verified: false
31
  - type: wer
32
  value: 13.72
33
  name: TEST WER (+LM)
34
+ verified: false
35
  - task:
36
+ type: automatic-speech-recognition
37
+ name: Speech Recognition
38
  dataset:
39
+ name: ATCOSIM corpus (Air Traffic Control Communications)
40
+ type: Jzuluaga/atcosim_corpus
41
+ config: test
42
+ split: test
43
  metrics:
44
  - type: wer
45
  value: 15.31
46
  name: TEST WER
47
+ verified: false
48
  - type: wer
49
  value: 11.88
50
  name: TEST WER (+LM)
51
+ verified: false
52
  ---
53
 
54
  # wav2vec2-large-960h-lv60-self-en-atc-uwb-atcc