From 1596f6f414f6f41da66506debb1dff19fffeb3ec Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 24 六月 2024 11:55:17 +0800
Subject: [PATCH] fixbug hotwords
---
funasr/tokenizer/whisper_tokenizer.py | 59 ++++++++++++++++++++++++++++++++++++++++-------------------
1 files changed, 40 insertions(+), 19 deletions(-)
diff --git a/funasr/tokenizer/whisper_tokenizer.py b/funasr/tokenizer/whisper_tokenizer.py
index 6684f25..bd96b83 100644
--- a/funasr/tokenizer/whisper_tokenizer.py
+++ b/funasr/tokenizer/whisper_tokenizer.py
@@ -1,24 +1,45 @@
-
-
from funasr.register import tables
+
@tables.register("tokenizer_classes", "WhisperTokenizer")
def WhisperTokenizer(**kwargs):
- try:
- from whisper.tokenizer import get_tokenizer
- except:
- print("Notice: If you want to use whisper, please `pip install -U openai-whisper`")
-
- language = kwargs.get("language", None)
- task = kwargs.get("task", "transcribe")
- is_multilingual = kwargs.get("is_multilingual", True)
- num_languages = kwargs.get("num_languages", 99)
- tokenizer = get_tokenizer(
- multilingual=is_multilingual,
- num_languages=num_languages,
- language=language,
- task=task,
- )
-
- return tokenizer
+ try:
+ from whisper.tokenizer import get_tokenizer
+ except:
+ print("Notice: If you want to use whisper, please `pip install -U openai-whisper`")
+ language = kwargs.get("language", None)
+ task = kwargs.get("task", "transcribe")
+ is_multilingual = kwargs.get("is_multilingual", True)
+ num_languages = kwargs.get("num_languages", 99)
+ tokenizer = get_tokenizer(
+ multilingual=is_multilingual,
+ num_languages=num_languages,
+ language=language,
+ task=task,
+ )
+
+ return tokenizer
+
+
+@tables.register("tokenizer_classes", "SenseVoiceTokenizer")
+def SenseVoiceTokenizer(**kwargs):
+ try:
+ from funasr.models.sense_voice.whisper_lib.tokenizer import get_tokenizer
+ except:
+ print("Notice: If you want to use whisper, please `pip install -U openai-whisper`")
+
+ language = kwargs.get("language", None)
+ task = kwargs.get("task", None)
+ is_multilingual = kwargs.get("is_multilingual", True)
+ num_languages = kwargs.get("num_languages", 8749)
+ vocab_path = kwargs.get("vocab_path", None)
+ tokenizer = get_tokenizer(
+ multilingual=is_multilingual,
+ num_languages=num_languages,
+ language=language,
+ task=task,
+ vocab_path=vocab_path,
+ )
+
+ return tokenizer
--
Gitblit v1.9.1