问如何使用时间戳注释标记和提取音频

EN

import io
import pandas
import numpy as np
import librosa
import soundfile as sf
def read_data(annot, date_format):
  df = pandas.read_csv(annot, sep=',')

  # Use proper pandas datatypes
  df['Time'] = pandas.to_datetime(df['DateTime'], format=date_format)
  df['Duration'] = pandas.to_timedelta(df['Duration ms'], unit='ms')
  df = df.drop(columns=['DateTime', 'Duration ms'])

  # Compute start and end time of each segment
  # audio starts at time of first segment
  first = df['Time'].iloc[0]
  df['Start'] = df['Time'] - first
  df['End'] = df['Start'] + df['Duration']

  return df

def extract_segments(y, sr, segments):
  # compute segment regions in number of samples
  starts = np.floor(segments.Start.dt.total_seconds() * sr).astype(int)
  ends = np.ceil(segments.End.dt.total_seconds() * sr).astype(int)

  # slice the audio into segments
  i = 0
  for start, end in zip(starts, ends):
    audio_seg = y[start:end]
    print('extracting audio segment:', len(audio_seg), 'samples')
    
    # file name string
    # it takes 5 first character of Action
    # and converts start and end time 
    file_name = str(segments.Activity[i][:5]) + \
    '__' + \
    str(segments.Start[i]).split('s ')[1].replace(':','_') + \
    '__' + \
    str(segments.End[i]).split('s ')[1].replace(':','_') + ".wav"
    
    sf.write(file_name, audio_seg, sr)
    i += 1
segments = read_data("annot.csv", date_format="%m/%d/%y %H:%M:%S:%f")
segments

y, sr = librosa.load("audio.wav", sr=16000, duration=2027)
extract_segments(y, sr, segments)