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