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/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