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/runtime/python/onnxruntime/funasr_onnx/utils/utils.py | 34 +++++++++++++++++++++++++++++++++-
1 files changed, 33 insertions(+), 1 deletions(-)
diff --git a/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py b/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
index fccd5a0..0df954e 100644
--- a/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
+++ b/funasr/runtime/python/onnxruntime/funasr_onnx/utils/utils.py
@@ -215,6 +215,38 @@
if not model_path.is_file():
raise FileExistsError(f'{model_path} is not a file.')
+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
+
+def code_mix_split_words(text: str):
+ words = []
+ segs = text.split()
+ for seg in segs:
+ # There is no space in seg.
+ current_word = ""
+ for c in seg:
+ if len(c.encode()) == 1:
+ # This is an ASCII char.
+ current_word += c
+ else:
+ # This is a Chinese char.
+ if len(current_word) > 0:
+ words.append(current_word)
+ current_word = ""
+ words.append(c)
+ if len(current_word) > 0:
+ words.append(current_word)
+ return words
def read_yaml(yaml_path: Union[str, Path]) -> Dict:
if not Path(yaml_path).exists():
@@ -226,7 +258,7 @@
@functools.lru_cache()
-def get_logger(name='rapdi_paraformer'):
+def get_logger(name='funasr_onnx'):
"""Initialize and get a logger by name.
If the logger has not been initialized, this method will initialize the
logger by adding one or two handlers, otherwise the initialized logger will
--
Gitblit v1.9.1