From 26d642bfdf59a50365a9c8158acb223cae1004dc Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 23 四月 2024 20:13:44 +0800
Subject: [PATCH] Dev gzf exp (#1651)
---
funasr/auto/auto_model.py | 4 +++-
1 files changed, 3 insertions(+), 1 deletions(-)
diff --git a/funasr/auto/auto_model.py b/funasr/auto/auto_model.py
index 630c390..ba8881a 100644
--- a/funasr/auto/auto_model.py
+++ b/funasr/auto/auto_model.py
@@ -175,6 +175,8 @@
kwargs["token_list"] = tokenizer.token_list if hasattr(tokenizer, "token_list") else None
kwargs["token_list"] = tokenizer.get_vocab() if hasattr(tokenizer, "get_vocab") else kwargs["token_list"]
vocab_size = len(kwargs["token_list"]) if kwargs["token_list"] is not None else -1
+ if vocab_size == -1 and hasattr(tokenizer, "get_vocab_size"):
+ vocab_size = tokenizer.get_vocab_size()
else:
vocab_size = -1
kwargs["tokenizer"] = tokenizer
@@ -415,7 +417,7 @@
return_raw_text = kwargs.get('return_raw_text', False)
# step.3 compute punc model
if self.punc_model is not None:
- if not len(result["text"]):
+ if not len(result["text"].strip()):
if return_raw_text:
result['raw_text'] = ''
else:
--
Gitblit v1.9.1