From 6427c834dfd97b1f05c6659cdc7ccf010bf82fe1 Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 24 四月 2023 19:50:07 +0800
Subject: [PATCH] update
---
funasr/datasets/preprocessor.py | 14 ++++++++++++++
1 files changed, 14 insertions(+), 0 deletions(-)
diff --git a/funasr/datasets/preprocessor.py b/funasr/datasets/preprocessor.py
index 98cca1d..afeff4e 100644
--- a/funasr/datasets/preprocessor.py
+++ b/funasr/datasets/preprocessor.py
@@ -800,3 +800,17 @@
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)
+
+
+def split_to_mini_sentence(words: list, word_limit: int = 20):
+ assert word_limit > 1
+ if len(words) <= word_limit:
+ return [words]
+ sentences = []
+ length = len(words)
+ sentence_len = length // word_limit
+ for i in range(sentence_len):
+ 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
--
Gitblit v1.9.1