From d0cd484fdc21c06b8bc892bb2ab1c2a25fb1da8a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 31 三月 2023 15:05:37 +0800
Subject: [PATCH] export

---
 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