Commit @e8bd61d37bdea2ca7e304f8c19774bbd3b28dd85 - yjyoon/whisper_streaming

Y
List All
Feedback
- This Project
- All Projects

Dominik Macháček 2023-11-27

create_tokenizer in documentation

#25

@e8bd61d37bdea2ca7e304f8c19774bbd3b28dd85

b99832f

e8bd61d

README.md

--- README.md

+++ README.md


 src_lan = "en"  # source language
 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
 # set options:
 # 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:

Add a comment

Open 0
Closed 0

List

...	...	@@ -126,14 +126,14 @@
126	126	src_lan = "en" # source language
127	127	tgt_lan = "en" # target language -- same as source for ASR, "en" if translate task is used
128	128
129		-
130	129	asr = FasterWhisperASR(lan, "large-v2") # loads and wraps Whisper model
131	130	# set options:
132	131	# asr.set_translate_task() # it will translate from lan into English
133		-# asr.use_vad() # set using VAD
	132	+# asr.use_vad() # set using VAD
134	133
	134	+tokenizer = create_tokenizer(tgt_lan) # sentence segmenter for the target language
135	135
136		-online = OnlineASRProcessor(tgt_lan, asr) # create processing object
	136	+online = OnlineASRProcessor(asr, tokenizer) # create processing object
137	137
138	138
139	139	while audio_has_not_ended: # processing loop:

Delete comment