From ac4af1d3bff0fcc8cb2beb9d1e852f5a6295e48d Mon Sep 17 00:00:00 2001
From: lingyunfly <121302812+lingyunfly@users.noreply.github.com>
Date: 星期五, 14 四月 2023 20:29:41 +0800
Subject: [PATCH] updata vad
---
funasr/datasets/preprocessor.py | 5 +++--
1 files changed, 3 insertions(+), 2 deletions(-)
diff --git a/funasr/datasets/preprocessor.py b/funasr/datasets/preprocessor.py
index afeff4e..1adca05 100644
--- a/funasr/datasets/preprocessor.py
+++ b/funasr/datasets/preprocessor.py
@@ -786,6 +786,7 @@
) -> Dict[str, np.ndarray]:
for i in range(self.num_tokenizer):
text_name = self.text_name[i]
+ #import pdb; pdb.set_trace()
if text_name in data and self.tokenizer[i] is not None:
text = data[text_name]
text = self.text_cleaner(text)
@@ -800,7 +801,7 @@
data[self.vad_name] = np.array([vad], dtype=np.int64)
text_ints = self.token_id_converter[i].tokens2ids(tokens)
data[text_name] = np.array(text_ints, dtype=np.int64)
-
+ return data
def split_to_mini_sentence(words: list, word_limit: int = 20):
assert word_limit > 1
@@ -813,4 +814,4 @@
sentences.append(words[i * word_limit:(i + 1) * word_limit])
if length % word_limit > 0:
sentences.append(words[sentence_len * word_limit:])
- return sentences
\ No newline at end of file
+ return sentences
--
Gitblit v1.9.1