aishell example

游雁

2024-02-19 94de39dde2e616a01683c518023d0fab72b4e103

 funasr/utils/timestamp_tools.py

@@ -1,36 +1,61 @@
import torch
import copy
import codecs
import logging
import argparse
import numpy as np
from typing import Any, List, Tuple, Union
# import edit_distance
from itertools import zip_longest


def cif_wo_hidden(alphas, threshold):
    batch_size, len_time = alphas.size()
    # loop varss
    integrate = torch.zeros([batch_size], device=alphas.device)
    # intermediate vars along time
    list_fires = []
    for t in range(len_time):
        alpha = alphas[:, t]
        integrate += alpha
        list_fires.append(integrate)
        fire_place = integrate >= threshold
        integrate = torch.where(fire_place,
                                integrate - torch.ones([batch_size], device=alphas.device)*threshold,
                                integrate)
    fires = torch.stack(list_fires, 1)
    return fires


def ts_prediction_lfr6_standard(us_alphas, 
                       us_cif_peak, 
                       us_peaks, 
                       char_list, 
                       vad_offset=0.0, 
                       end_time=None, 
                       force_time_shift=-1.5
                       force_time_shift=-1.5,
                       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
    if len(us_alphas.shape) == 2:
        alphas, cif_peak = us_alphas[0], us_cif_peak[0]  # support inference batch_size=1 only
        alphas, peaks = us_alphas[0], us_peaks[0]  # support inference batch_size=1 only
    else:
        alphas, cif_peak = us_alphas, us_cif_peak
    num_frames = cif_peak.shape[0]
        alphas, peaks = us_alphas, us_peaks
    if char_list[-1] == '</s>':
        char_list = char_list[:-1]
    fire_place = torch.where(peaks>1.0-1e-4)[0].cpu().numpy() + force_time_shift  # total offset
    if len(fire_place) != len(char_list) + 1:
        alphas /= (alphas.sum() / (len(char_list) + 1))
        alphas = alphas.unsqueeze(0)
        peaks = cif_wo_hidden(alphas, threshold=1.0-1e-4)[0]
        fire_place = torch.where(peaks>1.0-1e-4)[0].cpu().numpy() + force_time_shift  # total offset
    num_frames = peaks.shape[0]
    timestamp_list = []
    new_char_list = []
    # for bicif model trained with large data, cif2 actually fires when a character starts
    # so treat the frames between two peaks as the duration of the former token
    fire_place = torch.where(cif_peak>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
    fire_place = torch.where(peaks>1.0-1e-4)[0].cpu().numpy() + force_time_shift  # total offset
    # 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>')
@@ -63,6 +88,8 @@
            timestamp_list[i][1] = timestamp_list[i][1] + vad_offset / 1000.0
    res_txt = ""
    for char, timestamp in zip(new_char_list, timestamp_list):
        #if char != '<sil>':
        if not sil_in_str and char == '<sil>': continue
        res_txt += "{} {} {};".format(char, str(timestamp[0]+0.0005)[:5], str(timestamp[1]+0.0005)[:5])
    res = []
    for char, timestamp in zip(new_char_list, timestamp_list):
@@ -71,54 +98,63 @@
    return res_txt, res


def time_stamp_sentence(punc_id_list, time_stamp_postprocessed, text_postprocessed):
def timestamp_sentence(punc_id_list, timestamp_postprocessed, text_postprocessed):
    punc_list = ['，', '。', '？', '、']
    res = []
    if text_postprocessed is None:
        return res
    if time_stamp_postprocessed is None:
    if timestamp_postprocessed is None:
        return res
    if len(time_stamp_postprocessed) == 0:
    if len(timestamp_postprocessed) == 0:
        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]
            "start": timestamp_postprocessed[0][0],
            "end": timestamp_postprocessed[-1][1],
            "timestamp": timestamp_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 = ''
    sentence_start = time_stamp_postprocessed[0][0]
    if len(punc_id_list) != len(timestamp_postprocessed):
        logging.warning("length mismatch between punc and timestamp")
    sentence_text = ""
    sentence_text_seg = ""
    ts_list = []
    sentence_start = timestamp_postprocessed[0][0]
    sentence_end = timestamp_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, timestamp_postprocessed, texts, fillvalue=None))
    for punc_stamp_text in punc_stamp_text_list:
        punc_id, timestamp, 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(timestamp)

        punc_id = int(punc_id) if punc_id is not None else 1
        sentence_end = timestamp[1] if timestamp 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,
                "timestamp": 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