From c644ac8f58895b9e29e9cfca79465fd2c0efaa5a Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 21 十一月 2023 14:09:01 +0800
Subject: [PATCH] funasr v2 setup
---
funasr/utils/timestamp_tools.py | 222 +++++++++++++++++++++++++++---------------------------
1 files changed, 111 insertions(+), 111 deletions(-)
diff --git a/funasr/utils/timestamp_tools.py b/funasr/utils/timestamp_tools.py
index 6594273..c463f0c 100644
--- a/funasr/utils/timestamp_tools.py
+++ b/funasr/utils/timestamp_tools.py
@@ -3,7 +3,7 @@
import logging
import argparse
import numpy as np
-import edit_distance
+# import edit_distance
from itertools import zip_longest
@@ -160,112 +160,112 @@
return res
-class AverageShiftCalculator():
- def __init__(self):
- logging.warning("Calculating average shift.")
- def __call__(self, file1, file2):
- uttid_list1, ts_dict1 = self.read_timestamps(file1)
- uttid_list2, ts_dict2 = self.read_timestamps(file2)
- uttid_intersection = self._intersection(uttid_list1, uttid_list2)
- res = self.as_cal(uttid_intersection, ts_dict1, ts_dict2)
- logging.warning("Average shift of {} and {}: {}.".format(file1, file2, str(res)[:8]))
- logging.warning("Following timestamp pair differs most: {}, detail:{}".format(self.max_shift, self.max_shift_uttid))
-
- def _intersection(self, list1, list2):
- set1 = set(list1)
- set2 = set(list2)
- if set1 == set2:
- logging.warning("Uttid same checked.")
- return set1
- itsc = list(set1 & set2)
- logging.warning("Uttid differs: file1 {}, file2 {}, lines same {}.".format(len(list1), len(list2), len(itsc)))
- return itsc
-
- def read_timestamps(self, file):
- # read timestamps file in standard format
- uttid_list = []
- ts_dict = {}
- with codecs.open(file, 'r') as fin:
- for line in fin.readlines():
- text = ''
- ts_list = []
- line = line.rstrip()
- uttid = line.split()[0]
- uttid_list.append(uttid)
- body = " ".join(line.split()[1:])
- for pd in body.split(';'):
- if not len(pd): continue
- # pdb.set_trace()
- char, start, end = pd.lstrip(" ").split(' ')
- text += char + ','
- ts_list.append((float(start), float(end)))
- # ts_lists.append(ts_list)
- ts_dict[uttid] = (text[:-1], ts_list)
- logging.warning("File {} read done.".format(file))
- return uttid_list, ts_dict
-
- def _shift(self, filtered_timestamp_list1, filtered_timestamp_list2):
- shift_time = 0
- for fts1, fts2 in zip(filtered_timestamp_list1, filtered_timestamp_list2):
- shift_time += abs(fts1[0] - fts2[0]) + abs(fts1[1] - fts2[1])
- num_tokens = len(filtered_timestamp_list1)
- return shift_time, num_tokens
-
- def as_cal(self, uttid_list, ts_dict1, ts_dict2):
- # calculate average shift between timestamp1 and timestamp2
- # when characters differ, use edit distance alignment
- # and calculate the error between the same characters
- self._accumlated_shift = 0
- self._accumlated_tokens = 0
- self.max_shift = 0
- self.max_shift_uttid = None
- for uttid in uttid_list:
- (t1, ts1) = ts_dict1[uttid]
- (t2, ts2) = ts_dict2[uttid]
- _align, _align2, _align3 = [], [], []
- fts1, fts2 = [], []
- _t1, _t2 = [], []
- sm = edit_distance.SequenceMatcher(t1.split(','), t2.split(','))
- s = sm.get_opcodes()
- for j in range(len(s)):
- if s[j][0] == "replace" or s[j][0] == "insert":
- _align.append(0)
- if s[j][0] == "replace" or s[j][0] == "delete":
- _align3.append(0)
- elif s[j][0] == "equal":
- _align.append(1)
- _align3.append(1)
- else:
- continue
- # use s to index t2
- for a, ts , t in zip(_align, ts2, t2.split(',')):
- if a:
- fts2.append(ts)
- _t2.append(t)
- sm2 = edit_distance.SequenceMatcher(t2.split(','), t1.split(','))
- s = sm2.get_opcodes()
- for j in range(len(s)):
- if s[j][0] == "replace" or s[j][0] == "insert":
- _align2.append(0)
- elif s[j][0] == "equal":
- _align2.append(1)
- else:
- continue
- # use s2 tp index t1
- for a, ts, t in zip(_align3, ts1, t1.split(',')):
- if a:
- fts1.append(ts)
- _t1.append(t)
- if len(fts1) == len(fts2):
- shift_time, num_tokens = self._shift(fts1, fts2)
- self._accumlated_shift += shift_time
- self._accumlated_tokens += num_tokens
- if shift_time/num_tokens > self.max_shift:
- self.max_shift = shift_time/num_tokens
- self.max_shift_uttid = uttid
- else:
- logging.warning("length mismatch")
- return self._accumlated_shift / self._accumlated_tokens
+# class AverageShiftCalculator():
+# def __init__(self):
+# logging.warning("Calculating average shift.")
+# def __call__(self, file1, file2):
+# uttid_list1, ts_dict1 = self.read_timestamps(file1)
+# uttid_list2, ts_dict2 = self.read_timestamps(file2)
+# uttid_intersection = self._intersection(uttid_list1, uttid_list2)
+# res = self.as_cal(uttid_intersection, ts_dict1, ts_dict2)
+# logging.warning("Average shift of {} and {}: {}.".format(file1, file2, str(res)[:8]))
+# logging.warning("Following timestamp pair differs most: {}, detail:{}".format(self.max_shift, self.max_shift_uttid))
+#
+# def _intersection(self, list1, list2):
+# set1 = set(list1)
+# set2 = set(list2)
+# if set1 == set2:
+# logging.warning("Uttid same checked.")
+# return set1
+# itsc = list(set1 & set2)
+# logging.warning("Uttid differs: file1 {}, file2 {}, lines same {}.".format(len(list1), len(list2), len(itsc)))
+# return itsc
+#
+# def read_timestamps(self, file):
+# # read timestamps file in standard format
+# uttid_list = []
+# ts_dict = {}
+# with codecs.open(file, 'r') as fin:
+# for line in fin.readlines():
+# text = ''
+# ts_list = []
+# line = line.rstrip()
+# uttid = line.split()[0]
+# uttid_list.append(uttid)
+# body = " ".join(line.split()[1:])
+# for pd in body.split(';'):
+# if not len(pd): continue
+# # pdb.set_trace()
+# char, start, end = pd.lstrip(" ").split(' ')
+# text += char + ','
+# ts_list.append((float(start), float(end)))
+# # ts_lists.append(ts_list)
+# ts_dict[uttid] = (text[:-1], ts_list)
+# logging.warning("File {} read done.".format(file))
+# return uttid_list, ts_dict
+#
+# def _shift(self, filtered_timestamp_list1, filtered_timestamp_list2):
+# shift_time = 0
+# for fts1, fts2 in zip(filtered_timestamp_list1, filtered_timestamp_list2):
+# shift_time += abs(fts1[0] - fts2[0]) + abs(fts1[1] - fts2[1])
+# num_tokens = len(filtered_timestamp_list1)
+# return shift_time, num_tokens
+#
+# # def as_cal(self, uttid_list, ts_dict1, ts_dict2):
+# # # calculate average shift between timestamp1 and timestamp2
+# # # when characters differ, use edit distance alignment
+# # # and calculate the error between the same characters
+# # self._accumlated_shift = 0
+# # self._accumlated_tokens = 0
+# # self.max_shift = 0
+# # self.max_shift_uttid = None
+# # for uttid in uttid_list:
+# # (t1, ts1) = ts_dict1[uttid]
+# # (t2, ts2) = ts_dict2[uttid]
+# # _align, _align2, _align3 = [], [], []
+# # fts1, fts2 = [], []
+# # _t1, _t2 = [], []
+# # sm = edit_distance.SequenceMatcher(t1.split(','), t2.split(','))
+# # s = sm.get_opcodes()
+# # for j in range(len(s)):
+# # if s[j][0] == "replace" or s[j][0] == "insert":
+# # _align.append(0)
+# # if s[j][0] == "replace" or s[j][0] == "delete":
+# # _align3.append(0)
+# # elif s[j][0] == "equal":
+# # _align.append(1)
+# # _align3.append(1)
+# # else:
+# # continue
+# # # use s to index t2
+# # for a, ts , t in zip(_align, ts2, t2.split(',')):
+# # if a:
+# # fts2.append(ts)
+# # _t2.append(t)
+# # sm2 = edit_distance.SequenceMatcher(t2.split(','), t1.split(','))
+# # s = sm2.get_opcodes()
+# # for j in range(len(s)):
+# # if s[j][0] == "replace" or s[j][0] == "insert":
+# # _align2.append(0)
+# # elif s[j][0] == "equal":
+# # _align2.append(1)
+# # else:
+# # continue
+# # # use s2 tp index t1
+# # for a, ts, t in zip(_align3, ts1, t1.split(',')):
+# # if a:
+# # fts1.append(ts)
+# # _t1.append(t)
+# # if len(fts1) == len(fts2):
+# # shift_time, num_tokens = self._shift(fts1, fts2)
+# # self._accumlated_shift += shift_time
+# # self._accumlated_tokens += num_tokens
+# # if shift_time/num_tokens > self.max_shift:
+# # self.max_shift = shift_time/num_tokens
+# # self.max_shift_uttid = uttid
+# # else:
+# # logging.warning("length mismatch")
+# # return self._accumlated_shift / self._accumlated_tokens
def convert_external_alphas(alphas_file, text_file, output_file):
@@ -311,10 +311,10 @@
def main(args):
- if args.mode == 'cal_aas':
- asc = AverageShiftCalculator()
- asc(args.input, args.input2)
- elif args.mode == 'read_ext_alphas':
+ # if args.mode == 'cal_aas':
+ # asc = AverageShiftCalculator()
+ # asc(args.input, args.input2)
+ if args.mode == 'read_ext_alphas':
convert_external_alphas(args.input, args.input2, args.output)
else:
logging.error("Mode {} not in SUPPORTED_MODES: {}.".format(args.mode, SUPPORTED_MODES))
--
Gitblit v1.9.1