From 3a4281f4959534b1bf5d01acf0085f4f8e6f2ec8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期五, 05 七月 2024 00:55:32 +0800
Subject: [PATCH] 优化speakid和语句匹配逻辑，部分解决speakid不从0递增问题 (#1870)
---
funasr/tokenizer/hf_tokenizer.py | 18 ++++++++----------
1 files changed, 8 insertions(+), 10 deletions(-)
diff --git a/funasr/tokenizer/hf_tokenizer.py b/funasr/tokenizer/hf_tokenizer.py
index c856b3d..1ac7ae2 100644
--- a/funasr/tokenizer/hf_tokenizer.py
+++ b/funasr/tokenizer/hf_tokenizer.py
@@ -1,15 +1,13 @@
-
-try:
- from transformers import AutoTokenizer
-except:
- print("If you want to use hugging, please `pip install -U transformers`")
-
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)
- tokenizer = AutoTokenizer.from_pretrained(init_param_path)
-
- return tokenizer
-
+ return tokenizer
--
Gitblit v1.9.1