Hugging Face's logo

espnet
/
owls_4B_180K

Automatic Speech Recognition
ESPnet
multilingual
audio
speech-translation
Model card Files Community
wanchichen commited on
Commit
4140c35
·
verified ·
1 Parent(s): dc4d7cf

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -35,7 +35,7 @@ You can use this model in your projects with the following code:
35
  from espnet2.bin.s2t_inference import Speech2Text
36
 
37
  model = Speech2Text.from_pretrained(
38
- "espnet/owsm_v3.2"
39
  )
40
 
41
  speech, rate = soundfile.read("speech.wav")
 
35
  from espnet2.bin.s2t_inference import Speech2Text
36
 
37
  model = Speech2Text.from_pretrained(
38
+ "espnet/owls_4B_180K"
39
  )
40
 
41
  speech, rate = soundfile.read("speech.wav")