From 4f8bce944e273e317cb84c7046ea514b9d958b4b Mon Sep 17 00:00:00 2001
From: zhuzizyf <42790740+zhuzizyf@users.noreply.github.com>
Date: 星期六, 22 四月 2023 14:54:49 +0800
Subject: [PATCH] Update FsmnVad.cc
---
funasr/datasets/large_datasets/utils/tokenize.py | 14 +++++++++-----
1 files changed, 9 insertions(+), 5 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index a016e4e..022d321 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -19,6 +19,7 @@
def seg_tokenize(txt, seg_dict):
out_txt = ""
for word in txt:
+ word = word.lower()
if word in seg_dict:
out_txt += seg_dict[word] + " "
else:
@@ -28,23 +29,26 @@
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)
- txt = forward_segment("".join(text).lower(), seg_dict)
- text = seg_tokenize(txt, seg_dict)
+ text = seg_tokenize(text, seg_dict)
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