admin-valentin/WhisperLiveKit
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

create_tokenizer in documentation

Browse source 
#25
This commit is contained in:
Dominik Macháček 2023-11-26 16:11:42 +01:00 committed by GitHub
parent 483badf85d
commit 878f11cdb7
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
README.md
View file

@ -126,14 +126,14 @@ from whisper_online import *
src_lan = "en" # source language src_lan = "en" # source language
tgt_lan = "en" # target language -- same as source for ASR, "en" if translate task is used tgt_lan = "en" # target language -- same as source for ASR, "en" if translate task is used
asr = FasterWhisperASR(lan, "large-v2") # loads and wraps Whisper model asr = FasterWhisperASR(lan, "large-v2") # loads and wraps Whisper model
# set options: # set options:
# asr.set_translate_task() # it will translate from lan into English # asr.set_translate_task() # it will translate from lan into English
# asr.use_vad() # set using VAD # asr.use_vad() # set using VAD
tokenizer = create_tokenizer(tgt_lan) # sentence segmenter for the target language
online = OnlineASRProcessor(tgt_lan, asr) # create processing object online = OnlineASRProcessor(asr, tokenizer) # create processing object
while audio_has_not_ended: # processing loop: while audio_has_not_ended: # processing loop: