update AverageShiftCalculator in utils

shixian.shi

2023-03-13 71d466e7451435eefb604f22576aba04bd39e285

update AverageShiftCalculator in utils

 funasr/utils/timestamp_tools.py

@@ -1,6 +1,10 @@
from scipy.fftpack import shift
import torch
import copy
import codecs
import logging
import edit_distance
import argparse
import numpy as np
from typing import Any, List, Tuple, Union

@@ -121,4 +125,139 @@
    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_uttid))

    def _intersection(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):
        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


SUPPORTED_MODES = ['cal_aas']


def main(args):
    if args.mode == 'cal_aas':
        asc = AverageShiftCalculator()
        asc(args.input, args.input2)
    else:
        logging.error("Mode {} not in SUPPORTED_MODES: {}.".format(args.mode, SUPPORTED_MODES))


if __name__ == '__main__':
    parser = argparse.ArgumentParser(description='timestamp tools')
    parser.add_argument('--mode', 
                        default=None, 
                        type=str, 
                        choices=SUPPORTED_MODES, 
                        help='timestamp related toolbox')
    parser.add_argument('--input', default=None, type=str, help='input file path')
    parser.add_argument('--output', default=None, type=str, help='output file name')
    parser.add_argument('--input2', default=None, type=str, help='input2 file path')
    parser.add_argument('--kaldi-ts-type', 
                        default='v2', 
                        type=str, 
                        choices=['v0', 'v1', 'v2'], 
                        help='kaldi timestamp to write')
    args = parser.parse_args()
    main(args)