From 4ace5a95b052d338947fc88809a440ccd55cf6b4 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 16 十一月 2023 16:39:52 +0800
Subject: [PATCH] funasr pages
---
funasr/datasets/large_datasets/utils/tokenize.py | 40 +++++++++++++++++++++++++++++++---------
1 files changed, 31 insertions(+), 9 deletions(-)
diff --git a/funasr/datasets/large_datasets/utils/tokenize.py b/funasr/datasets/large_datasets/utils/tokenize.py
index d8ceff2..34a97c1 100644
--- a/funasr/datasets/large_datasets/utils/tokenize.py
+++ b/funasr/datasets/large_datasets/utils/tokenize.py
@@ -1,6 +1,7 @@
#!/usr/bin/env python
import re
import numpy as np
+from funasr.datasets.large_datasets.utils.hotword_utils import sample_hotword
def forward_segment(text, seg_dict):
word_list = []
@@ -17,38 +18,59 @@
return word_list
def seg_tokenize(txt, seg_dict):
+ pattern = re.compile(r'^[\u4E00-\u9FA50-9]+$')
out_txt = ""
for word in txt:
+ word = word.lower()
if word in seg_dict:
out_txt += seg_dict[word] + " "
else:
- out_txt += "<unk>" + " "
+ if pattern.match(word):
+ for char in word:
+ if char in seg_dict:
+ out_txt += seg_dict[char] + " "
+ else:
+ out_txt += "<unk>" + " "
+ else:
+ out_txt += "<unk>" + " "
return out_txt.strip().split()
def tokenize(data,
vocab=None,
seg_dict=None,
punc_dict=None,
- bpe_tokenizer=None):
+ bpe_tokenizer=None,
+ hw_config=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))
-
+ 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)
+ if 'hw_tag' in data:
+ pre_index = None
+ if hw_config['pre_hwlist'] is not None and hw_config['pre_prob'] > 0:
+ # enable preset hotword detect in sampling
+ for hw in hw_config['pre_hwlist']:
+ hw = " ".join(seg_tokenize(hw, seg_dict))
+ _find = " ".join(text).find(hw)
+ if _find != -1:
+ # _find = text[:_find].count(" ") # bpe sometimes
+ pre_index = [_find, _find + max(hw.count(" "), 1)]
+ break
+ hotword_indxs = sample_hotword(length, **hw_config, pre_index=pre_index)
+ data['hotword_indxs'] = hotword_indxs
+ del data['hw_tag']
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