From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
funasr/tokenizer/hf_tokenizer.py | 19 ++++++++-----------
1 files changed, 8 insertions(+), 11 deletions(-)
diff --git a/funasr/tokenizer/hf_tokenizer.py b/funasr/tokenizer/hf_tokenizer.py
index b6043e9..1ac7ae2 100644
--- a/funasr/tokenizer/hf_tokenizer.py
+++ b/funasr/tokenizer/hf_tokenizer.py
@@ -1,16 +1,13 @@
-
-
-
from funasr.register import tables
+
@tables.register("tokenizer_classes", "HuggingfaceTokenizer")
def HuggingfaceTokenizer(init_param_path, **kwargs):
- try:
- from transformers import AutoTokenizer
- except:
- # print("If you want to use hugging, please `pip install -U transformers`")
- pass
- tokenizer = AutoTokenizer.from_pretrained(init_param_path)
-
- return tokenizer
+ try:
+ from transformers import AutoTokenizer
+ except:
+ # print("If you want to use hugging, please `pip install -U transformers`")
+ pass
+ tokenizer = AutoTokenizer.from_pretrained(init_param_path)
+ return tokenizer
--
Gitblit v1.9.1