wav2txt.py

#!/usr/bin/env python

import os
import sys
import numpy as np
import wave
import struct
import math
import speech_recognition as sr

def wav2txt(wav_fname):
    r = sr.Recognizer()
    with sr.AudioFile(wav_fname) as source:
            audio = r.record(source)
    try:
        text = r.recognize_google(audio, language="ja-JP")
    except sr.UnknownValueError:
        print("Google Web Speech API could not recognize speech.")
    except sr.RequestError as e:
        print("Could not request Google Web Speech API." " {0}".format(e))
    else:
        return text

def cut_wav(wav_fname, time, out_dir):  
    wr = wave.open(wav_fname, 'r')
    ch = wr.getnchannels()
    width = wr.getsampwidth()
    fr = wr.getframerate()
    fn = wr.getnframes()
    total_time = 1.0 * fn / fr
    integer = math.floor(total_time) 
    t = int(time) 
    frames = int(ch * fr * t)
    num_cut = int(integer//t)

    print("Frame Rate: ", fr)
    print("Frame num: ", fn)
    print("Total time: ", total_time)
    print("Total time(integer)",integer)
    print("Time: ", t) 
    print("Frames: ", frames) 
    print("Number of cut: ",num_cut)

    data = wr.readframes(wr.getnframes())
    wr.close()
    X = np.frombuffer(data, dtype= "int16")

    out_txtf = out_dir + '/' + 'dialogue.txt'
    for i in range(num_cut):
        out_wavf = out_dir + '/' + str(i) + '.wav' 
        start_cut = i*frames
        end_cut = i*frames + frames
        print(start_cut)
        print(end_cut)
        Y = X[start_cut:end_cut]
        outd = struct.pack("h" * len(Y), *Y)

        ww = wave.open(out_wavf, 'w')
        ww.setnchannels(ch)
        ww.setsampwidth(width)
        ww.setframerate(fr)
        ww.writeframes(outd)
        ww.close()

        text = str(wav2txt(out_wavf))
        if not text == 'None':
                text = text.replace(' ', '\n')
                f = open(out_txtf, 'a')
                f.write('#-- ' + str(i) + 'min' +'\n' + text + '\n')
                f.close()

if __name__ == '__main__':
    wav_fname = sys.argv[1]
    out_dir = os.path.splitext(os.path.basename(wav_fname))[0]

    if os.path.exists(out_dir) == False:
            os.mkdir(out_dir)
    cut_wav(wav_fname, 60, out_dir)