From fce4e1d1b48f23cd8332e60afce3df8d6209a6a7 Mon Sep 17 00:00:00 2001
From: gaochangfeng <54253717+gaochangfeng@users.noreply.github.com>
Date: 星期四, 11 四月 2024 14:59:22 +0800
Subject: [PATCH] SenseVoice对富文本解码的参数 (#1608)
---
funasr/models/ct_transformer/model.py | 2 ++
1 files changed, 2 insertions(+), 0 deletions(-)
diff --git a/funasr/models/ct_transformer/model.py b/funasr/models/ct_transformer/model.py
index 57a23cc..edb398f 100644
--- a/funasr/models/ct_transformer/model.py
+++ b/funasr/models/ct_transformer/model.py
@@ -347,8 +347,10 @@
punc_array = punctuations
else:
punc_array = torch.cat([punc_array, punctuations], dim=0)
+
# post processing when using word level punc model
if self.jieba_usr_dict is not None:
+ punc_array = punc_array.reshape(-1)
len_tokens = len(tokens)
new_punc_array = copy.copy(punc_array).tolist()
# for i, (token, punc_id) in enumerate(zip(tokens[::-1], punc_array.tolist()[::-1])):
--
Gitblit v1.9.1