Hugging Face's logo

nvidia
/
stt_en_conformer_transducer_xlarge

Automatic Speech Recognition
NeMo
PyTorch
English
speech
audio
Transducer
Conformer
Transformer
NeMo
hf-asr-leaderboard
Eval Results
Model card Files
xet
Community
2
SKostandian commited on
Commit
9a8498b
·
verified ·
1 Parent(s): 96472b7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -4
README.md CHANGED
@@ -11,9 +11,9 @@ datasets:
11
  - National-Singapore-Corpus-Part-1
12
  - National-Singapore-Corpus-Part-6
13
  - vctk
14
- - VoxPopuli-(EN)
15
- - Europarl-ASR-(EN)
16
- - Multilingual-LibriSpeech-(2000-hours)
17
  - mozilla-foundation/common_voice_8_0
18
  - MLCommons/peoples_speech
19
  thumbnail: null
@@ -190,7 +190,8 @@ wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav
190
  ```
191
  Then simply do:
192
  ```
193
- asr_model.transcribe(['2086-149220-0033.wav'])
 
194
  ```
195
 
196
  ### Transcribing many audio files
 
11
  - National-Singapore-Corpus-Part-1
12
  - National-Singapore-Corpus-Part-6
13
  - vctk
14
+ - VoxPopuli
15
+ - Europarl-ASR
16
+ - Multilingual-LibriSpeech
17
  - mozilla-foundation/common_voice_8_0
18
  - MLCommons/peoples_speech
19
  thumbnail: null
 
190
  ```
191
  Then simply do:
192
  ```
193
+ output = asr_model.transcribe(['2086-149220-0033.wav'])
194
+ print(output[0].text)
195
  ```
196
 
197
  ### Transcribing many audio files