From 3a4281f4959534b1bf5d01acf0085f4f8e6f2ec8 Mon Sep 17 00:00:00 2001
From: wuhongsheng <664116298@qq.com>
Date: 星期五, 05 七月 2024 00:55:32 +0800
Subject: [PATCH] 优化speakid和语句匹配逻辑，部分解决speakid不从0递增问题 (#1870)
---
funasr/utils/postprocess_utils.py | 229 ++++++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 178 insertions(+), 51 deletions(-)
diff --git a/funasr/utils/postprocess_utils.py b/funasr/utils/postprocess_utils.py
index 72080ae..34f933c 100644
--- a/funasr/utils/postprocess_utils.py
+++ b/funasr/utils/postprocess_utils.py
@@ -1,23 +1,24 @@
# Copyright (c) Alibaba, Inc. and its affiliates.
import string
+import logging
from typing import Any, List, Union
def isChinese(ch: str):
- if '\u4e00' <= ch <= '\u9fff':
+ if "\u4e00" <= ch <= "\u9fff" or "\u0030" <= ch <= "\u0039" or ch == "@":
return True
return False
def isAllChinese(word: Union[List[Any], str]):
word_lists = []
- table = str.maketrans('', '', string.punctuation)
for i in word:
- cur = i.translate(table)
- cur = cur.replace(' ', '')
- cur = cur.replace('</s>', '')
- cur = cur.replace('<s>', '')
+ cur = i.replace(" ", "")
+ cur = cur.replace("</s>", "")
+ cur = cur.replace("<s>", "")
+ cur = cur.replace("<unk>", "")
+ cur = cur.replace("<OOV>", "")
word_lists.append(cur)
if len(word_lists) == 0:
@@ -31,19 +32,19 @@
def isAllAlpha(word: Union[List[Any], str]):
word_lists = []
- table = str.maketrans('', '', string.punctuation)
for i in word:
- cur = i.translate(table)
- cur = cur.replace(' ', '')
- cur = cur.replace('</s>', '')
- cur = cur.replace('<s>', '')
+ cur = i.replace(" ", "")
+ cur = cur.replace("</s>", "")
+ cur = cur.replace("<s>", "")
+ cur = cur.replace("<unk>", "")
+ cur = cur.replace("<OOV>", "")
word_lists.append(cur)
if len(word_lists) == 0:
return False
for ch in word_lists:
- if ch.isalpha() is False:
+ if ch.isalpha() is False and ch != "'":
return False
elif ch.isalpha() is True and isChinese(ch) is True:
return False
@@ -51,22 +52,28 @@
return True
-def abbr_dispose(words: List[Any]) -> List[Any]:
+# def abbr_dispose(words: List[Any]) -> List[Any]:
+def abbr_dispose(words: List[Any], time_stamp: List[List] = None) -> List[Any]:
words_size = len(words)
word_lists = []
abbr_begin = []
abbr_end = []
last_num = -1
+ ts_lists = []
+ ts_nums = []
+ ts_index = 0
for num in range(words_size):
if num <= last_num:
continue
- if len(words[num]) == 1 and words[num].encode('utf-8').isalpha():
- if num + 1 < words_size and words[
- num + 1] == ' ' and num + 2 < words_size and len(
- words[num +
- 2]) == 1 and words[num +
- 2].encode('utf-8').isalpha():
+ if len(words[num]) == 1 and words[num].encode("utf-8").isalpha():
+ if (
+ num + 1 < words_size
+ and words[num + 1] == " "
+ and num + 2 < words_size
+ and len(words[num + 2]) == 1
+ and words[num + 2].encode("utf-8").isalpha()
+ ):
# found the begin of abbr
abbr_begin.append(num)
num += 2
@@ -74,11 +81,13 @@
# to find the end of abbr
while True:
num += 1
- if num < words_size and words[num] == ' ':
+ if num < words_size and words[num] == " ":
num += 1
- if num < words_size and len(
- words[num]) == 1 and words[num].encode(
- 'utf-8').isalpha():
+ if (
+ num < words_size
+ and len(words[num]) == 1
+ and words[num].encode("utf-8").isalpha()
+ ):
abbr_end.pop()
abbr_end.append(num)
last_num = num
@@ -87,88 +96,206 @@
else:
break
+ for num in range(words_size):
+ if words[num] == " ":
+ ts_nums.append(ts_index)
+ else:
+ ts_nums.append(ts_index)
+ ts_index += 1
last_num = -1
for num in range(words_size):
if num <= last_num:
continue
if num in abbr_begin:
- word_lists.append(words[num].upper())
+ if time_stamp is not None:
+ begin = time_stamp[ts_nums[num]][0]
+ abbr_word = words[num].upper()
num += 1
while num < words_size:
if num in abbr_end:
- word_lists.append(words[num].upper())
+ abbr_word += words[num].upper()
last_num = num
break
else:
- if words[num].encode('utf-8').isalpha():
- word_lists.append(words[num].upper())
+ if words[num].encode("utf-8").isalpha():
+ abbr_word += words[num].upper()
num += 1
+ word_lists.append(abbr_word)
+ if time_stamp is not None:
+ end = time_stamp[ts_nums[num]][1]
+ ts_lists.append([begin, end])
else:
word_lists.append(words[num])
+ if time_stamp is not None and words[num] != " ":
+ begin = time_stamp[ts_nums[num]][0]
+ end = time_stamp[ts_nums[num]][1]
+ ts_lists.append([begin, end])
+ begin = end
- return word_lists
+ if time_stamp is not None:
+ return word_lists, ts_lists
+ else:
+ return word_lists
-def sentence_postprocess(words: List[Any]):
+def sentence_postprocess(words: List[Any], time_stamp: List[List] = None):
middle_lists = []
word_lists = []
- word_item = ''
+ word_item = ""
+ ts_lists = []
# wash words lists
for i in words:
- word = ''
+ word = ""
if isinstance(i, str):
word = i
else:
- word = i.decode('utf-8')
+ word = i.decode("utf-8")
- if word in ['<s>', '</s>', '<unk>']:
+ if word in ["<s>", "</s>", "<unk>", "<OOV>"]:
continue
else:
middle_lists.append(word)
# all chinese characters
if isAllChinese(middle_lists):
- for ch in middle_lists:
- word_lists.append(ch.replace(' ', ''))
+ for i, ch in enumerate(middle_lists):
+ word_lists.append(ch.replace(" ", ""))
+ if time_stamp is not None:
+ ts_lists = time_stamp
# all alpha characters
elif isAllAlpha(middle_lists):
- for ch in middle_lists:
- word = ''
- if '@@' in ch:
- word = ch.replace('@@', '')
+ ts_flag = True
+ for i, ch in enumerate(middle_lists):
+ if ts_flag and time_stamp is not None:
+ begin = time_stamp[i][0]
+ end = time_stamp[i][1]
+ word = ""
+ if "@@" in ch:
+ word = ch.replace("@@", "")
word_item += word
+ if time_stamp is not None:
+ ts_flag = False
+ end = time_stamp[i][1]
else:
word_item += ch
word_lists.append(word_item)
- word_lists.append(' ')
- word_item = ''
+ word_lists.append(" ")
+ word_item = ""
+ if time_stamp is not None:
+ ts_flag = True
+ end = time_stamp[i][1]
+ ts_lists.append([begin, end])
+ begin = end
# mix characters
else:
alpha_blank = False
- for ch in middle_lists:
- word = ''
+ ts_flag = True
+ begin = -1
+ end = -1
+ for i, ch in enumerate(middle_lists):
+ if ts_flag and time_stamp is not None:
+ begin = time_stamp[i][0]
+ end = time_stamp[i][1]
+ word = ""
if isAllChinese(ch):
if alpha_blank is True:
word_lists.pop()
word_lists.append(ch)
alpha_blank = False
- elif '@@' in ch:
- word = ch.replace('@@', '')
+ if time_stamp is not None:
+ ts_flag = True
+ ts_lists.append([begin, end])
+ begin = end
+ elif "@@" in ch:
+ word = ch.replace("@@", "")
word_item += word
alpha_blank = False
+ if time_stamp is not None:
+ ts_flag = False
+ end = time_stamp[i][1]
elif isAllAlpha(ch):
word_item += ch
word_lists.append(word_item)
- word_lists.append(' ')
- word_item = ''
+ word_lists.append(" ")
+ word_item = ""
alpha_blank = True
+ if time_stamp is not None:
+ ts_flag = True
+ end = time_stamp[i][1]
+ ts_lists.append([begin, end])
+ begin = end
else:
- raise ValueError('invalid character: {}'.format(ch))
+ word_lists.append(ch)
- word_lists = abbr_dispose(word_lists)
- sentence = ''.join(word_lists).strip()
- return sentence
+ if time_stamp is not None:
+ word_lists, ts_lists = abbr_dispose(word_lists, ts_lists)
+ real_word_lists = []
+ for ch in word_lists:
+ if ch != " ":
+ real_word_lists.append(ch)
+ sentence = " ".join(real_word_lists).strip()
+ return sentence, ts_lists, real_word_lists
+ else:
+ word_lists = abbr_dispose(word_lists)
+ real_word_lists = []
+ for ch in word_lists:
+ if ch != " ":
+ real_word_lists.append(ch)
+ sentence = "".join(word_lists).strip()
+ return sentence, real_word_lists
+
+
+def sentence_postprocess_sentencepiece(words):
+ middle_lists = []
+ word_lists = []
+ word_item = ""
+
+ # wash words lists
+ for i in words:
+ word = ""
+ if isinstance(i, str):
+ word = i
+ else:
+ word = i.decode("utf-8")
+
+ if word in ["<s>", "</s>", "<unk>", "<OOV>"]:
+ continue
+ else:
+ middle_lists.append(word)
+
+ # all alpha characters
+ for i, ch in enumerate(middle_lists):
+ word = ""
+ if "\u2581" in ch and i == 0:
+ word_item = ""
+ word = ch.replace("\u2581", "")
+ word_item += word
+ elif "\u2581" in ch and i != 0:
+ word_lists.append(word_item)
+ word_lists.append(" ")
+ word_item = ""
+ word = ch.replace("\u2581", "")
+ word_item += word
+ else:
+ word_item += ch
+ if word_item is not None:
+ word_lists.append(word_item)
+ # word_lists = abbr_dispose(word_lists)
+ real_word_lists = []
+ for ch in word_lists:
+ if ch != " ":
+ if ch == "i":
+ ch = ch.replace("i", "I")
+ elif ch == "i'm":
+ ch = ch.replace("i'm", "I'm")
+ elif ch == "i've":
+ ch = ch.replace("i've", "I've")
+ elif ch == "i'll":
+ ch = ch.replace("i'll", "I'll")
+ real_word_lists.append(ch)
+ sentence = "".join(word_lists)
+ return sentence, real_word_lists
--
Gitblit v1.9.1