From 24f73665e2d8ea8e4de2fe4f900bc539d7f7b989 Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期一, 17 四月 2023 15:49:45 +0800
Subject: [PATCH] Merge pull request #367 from alibaba-damo-academy/dev_lhn2
---
funasr/datasets/large_datasets/utils/tokenize.py | 20 ++++++++++----------
1 files changed, 10 insertions(+), 10 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index caeb426..5a2f921 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -18,26 +18,26 @@
def seg_tokenize(txt, seg_dict):
out_txt = ""
- pattern = re.compile(r"([\u4E00-\u9FA5A-Za-z0-9])")
for word in txt:
- if pattern.match(word):
- if word in seg_dict:
- out_txt += seg_dict[word] + " "
- else:
- out_txt += "<unk>" + " "
+ if word in seg_dict:
+ out_txt += seg_dict[word] + " "
else:
- continue
+ out_txt += "<unk>" + " "
return out_txt.strip().split()
def tokenize(data,
vocab=None,
seg_dict=None,
- punc_dict=None):
+ punc_dict=None,
+ bpe_tokenizer=None):
assert "text" in data
assert isinstance(vocab, dict)
text = data["text"]
token = []
vad = -2
+
+ if bpe_tokenizer is not None:
+ text = bpe_tokenizer.text2tokens("".join(text))
if seg_dict is not None:
assert isinstance(seg_dict, dict)
@@ -47,8 +47,8 @@
length = len(text)
for i in range(length):
x = text[i]
- if i == length-1 and "punc" in data and text[i].startswith("vad:"):
- vad = x[-1][4:]
+ if i == length-1 and "punc" in data and x.startswith("vad:"):
+ vad = x[4:]
if len(vad) == 0:
vad = -1
else:
--
Gitblit v1.9.1