Hugging Face's logo

nvidia
/
stt_en_conformer_ctc_large

Automatic Speech Recognition
NeMo
PyTorch
English
speech
audio
CTC
Conformer
Transformer
NeMo
hf-asr-leaderboard
Riva
Eval Results
Model card Files Community
2
smajumdar94 commited on
Commit
1e0341e
•
1 Parent(s): 2ecfee0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +63 -1
README.md CHANGED
@@ -1,15 +1,77 @@
1
  ---
2
  language: "en"
3
  library_name: nemo
4
- thumbnail:
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  tags:
6
  - automatic-speech-recognition
 
 
7
  - CTC
8
  - Conformer
9
  - Transformer
10
  - pytorch
11
  - NeMo
12
  license: mit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
13
  ---
14
  ## Model Overview
15
 
 
1
  ---
2
  language: "en"
3
  library_name: nemo
4
+ datasets:
5
+ - librispeech_asr
6
+ - fisher_corpus
7
+ - Switchboard-1
8
+ - WSJ-0
9
+ - WSJ-1
10
+ - National Singapore Corpus Part 1
11
+ - National Singapore Corpus Part 6
12
+ - vctk
13
+ - VoxPopuli (EN)
14
+ - Europarl-ASR (EN)
15
+ - Multilingual LibriSpeech (2000 hours)
16
+ - common_voice_7_0
17
+ thumbnail:
18
  tags:
19
  - automatic-speech-recognition
20
+ - speech
21
+ - audio
22
  - CTC
23
  - Conformer
24
  - Transformer
25
  - pytorch
26
  - NeMo
27
  license: mit
28
+ model-index:
29
+ - name: stt_en_conformer_ctc_large
30
+ results:
31
+ - task:
32
+ type: Automatic Speech Recognition
33
+ name: automatic-speech-recognition
34
+ dataset:
35
+ name: Librispeech (clean)
36
+ type: librispeech_asr
37
+ args: en
38
+ metrics:
39
+ - name: Test WER
40
+ type: wer
41
+ value: 2.2
42
+ - task:
43
+ type: Automatic Speech Recognition
44
+ name: automatic-speech-recognition
45
+ dataset:
46
+ name: Librispeech (other)
47
+ type: librispeech_asr
48
+ args: en
49
+ metrics:
50
+ - name: Test WER
51
+ type: wer
52
+ value: 4.3
53
+ - task:
54
+ type: Automatic Speech Recognition
55
+ name: automatic-speech-recognition
56
+ dataset:
57
+ name: Librispeech (other)
58
+ type: librispeech_asr
59
+ args: en
60
+ metrics:
61
+ - name: Test WER
62
+ type: wer
63
+ value: 4.3
64
+ - task:
65
+ type: Automatic Speech Recognition
66
+ name: automatic-speech-recognition
67
+ dataset:
68
+ name: Mozilla Common Voice 7.0
69
+ type: common_voice_7.0
70
+ args: en
71
+ metrics:
72
+ - name: Test WER
73
+ type: wer
74
+ value: 8.0
75
  ---
76
  ## Model Overview
77