TOLD/SOND: download sv model

志浩

2023-08-01 5cfdcfc45a042e338c2b2f4a08dab125de3fb5ee

 funasr/utils/timestamp_tools.py

@@ -1,14 +1,10 @@
from pydoc import TextRepr
from scipy.fftpack import shift
import torch
import copy
import codecs
import logging
import edit_distance
import argparse
import pdb
import numpy as np
from typing import Any, List, Tuple, Union
import edit_distance
from itertools import zip_longest


def ts_prediction_lfr6_standard(us_alphas, 
@@ -19,7 +15,7 @@
                       sil_in_str=True
                       ):
    if not len(char_list):
        return []
        return "", []
    START_END_THRESHOLD = 5
    MAX_TOKEN_DURATION = 12
    TIME_RATE = 10.0 * 6 / 1000 / 3  #  3 times upsampled
@@ -36,7 +32,14 @@
    # so treat the frames between two peaks as the duration of the former token
    fire_place = torch.where(peaks>1.0-1e-4)[0].cpu().numpy() + force_time_shift  # total offset
    num_peak = len(fire_place)
    assert num_peak == len(char_list) + 1 # number of peaks is supposed to be number of tokens + 1
    if num_peak != len(char_list) + 1:
        logging.warning("length mismatch, result might be incorrect.")
        logging.warning("num_peaks: {}, num_chars+1: {}, which is supposed to be same.".format(num_peak, len(char_list)+1))
    if num_peak > len(char_list) + 1:
        fire_place = fire_place[:len(char_list) - 1]
    elif num_peak < len(char_list) + 1:
        char_list = char_list[:num_peak + 1]
    # assert num_peak == len(char_list) + 1 # number of peaks is supposed to be number of tokens + 1
    # begin silence
    if fire_place[0] > START_END_THRESHOLD:
        # char_list.insert(0, '<sil>')
@@ -80,6 +83,7 @@


def time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed):
    punc_list = ['，', '。', '？', '、']
    res = []
    if text_postprocessed is None:
        return res
@@ -89,44 +93,54 @@
        return res
    if len(text_postprocessed) == 0:
        return res

    if punc_id_list is None or len(punc_id_list) == 0:
        res.append({
            'text': text_postprocessed.split(),
            "start": time_stamp_postprocessed[0][0],
            "end": time_stamp_postprocessed[-1][1]
            "end": time_stamp_postprocessed[-1][1],
            'text_seg': text_postprocessed.split(),
            "ts_list": time_stamp_postprocessed,
        })
        return res
    if len(punc_id_list) != len(time_stamp_postprocessed):
        res.append({
            'text': text_postprocessed.split(),
            "start": time_stamp_postprocessed[0][0],
            "end": time_stamp_postprocessed[-1][1]
        })
        return res

    sentence_text = ''
        print("  warning length mistach!!!!!!")
    sentence_text = ""
    sentence_text_seg = ""
    ts_list = []
    sentence_start = time_stamp_postprocessed[0][0]
    sentence_end = time_stamp_postprocessed[0][1]
    texts = text_postprocessed.split()
    for i in range(len(punc_id_list)):
        sentence_text += texts[i]
        if punc_id_list[i] == 2:
            sentence_text += ','
    punc_stamp_text_list = list(zip_longest(punc_id_list, time_stamp_postprocessed, texts, fillvalue=None))
    for punc_stamp_text in punc_stamp_text_list:
        punc_id, time_stamp, text = punc_stamp_text
        # sentence_text += text if text is not None else ''
        if text is not None:
            if 'a' <= text[0] <= 'z' or 'A' <= text[0] <= 'Z':
                sentence_text += ' ' + text
            elif len(sentence_text) and ('a' <= sentence_text[-1] <= 'z' or 'A' <= sentence_text[-1] <= 'Z'):
                sentence_text += ' ' + text
            else:
                sentence_text += text
            sentence_text_seg += text + ' '
        ts_list.append(time_stamp)

        punc_id = int(punc_id) if punc_id is not None else 1
        sentence_end = time_stamp[1] if time_stamp is not None else sentence_end

        if punc_id > 1:
            sentence_text += punc_list[punc_id - 2]
            res.append({
                'text': sentence_text,
                "start": sentence_start,
                "end": time_stamp_postprocessed[i][1]
                "end": sentence_end,
                "text_seg": sentence_text_seg,
                "ts_list": ts_list
            })
            sentence_text = ''
            sentence_start = time_stamp_postprocessed[i][1]
        elif punc_id_list[i] == 3:
            sentence_text += '.'
            res.append({
                'text': sentence_text,
                "start": sentence_start,
                "end": time_stamp_postprocessed[i][1]
            })
            sentence_text = ''
            sentence_start = time_stamp_postprocessed[i][1]
            sentence_text_seg = ''
            ts_list = []
            sentence_start = sentence_end
    return res