From 6e69d784e4814c3dbe35e8f70c6cf4b920c8b20b Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 19 三月 2025 23:10:13 +0800
Subject: [PATCH] 1. bug fix:list(mean)和list(var)，由于mean和var是numpy，导致写入到文件的格式错误，参考上面的话，大概率是list(mean.tolist())，其实外层list没有必要 (#2437)
---
funasr/tokenizer/whisper_tokenizer.py | 57 +++++++++++++++++++++++++++++++++++++++------------------
1 files changed, 39 insertions(+), 18 deletions(-)
diff --git a/funasr/tokenizer/whisper_tokenizer.py b/funasr/tokenizer/whisper_tokenizer.py
index 3fb5b64..bd96b83 100644
--- a/funasr/tokenizer/whisper_tokenizer.py
+++ b/funasr/tokenizer/whisper_tokenizer.py
@@ -1,24 +1,45 @@
-
-try:
- from whisper.tokenizer import get_tokenizer
-except:
- print("Notice: If you want to use whisper, please `pip install -U openai-whisper`")
-
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
+ 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