From 878f11cdb74266b5c3c0e3f2bdcc07358d2f0ec8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dominik=20Mach=C3=A1=C4=8Dek?=
 <Gldkslfmsd@users.noreply.github.com>
Date: Sun, 26 Nov 2023 16:11:42 +0100
Subject: [PATCH] create_tokenizer in documentation

#25
---
 README.md | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 480c8e7..265892c 100644
--- a/README.md
+++ b/README.md
@@ -126,14 +126,14 @@ from whisper_online import *
 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: