Этот скрипт будет работать с 30-секундным wav-файлом, но не с 10-минутным телефонным звонком, также в формате wav.Любая помощь будет оценена
Я скачал ffmpeg.
# Import necessary libraries
from pydub import AudioSegment
import speech_recognition as sr
import os
import pydub
chunk_count = 0
directory = os.fsencode(r'C:\Users\zach.blair\Downloads\speechRecognition\New folder')
# Text file to write the recognized audio
fh = open("recognized.txt", "w+")
for file in os.listdir(directory):
filename = os.fsdecode(file)
if filename.endswith(".wav"):
chunk_count += 1
# Input audio file to be sliced
audio = AudioSegment.from_file(filename,format="wav")
'''
Step #1 - Slicing the audio file into smaller chunks.
'''
# Length of the audiofile in milliseconds
n = len(audio)
# Variable to count the number of sliced chunks
counter = 1
# Interval length at which to slice the audio file.
interval = 20 * 1000
# Length of audio to overlap.
overlap = 1 * 1000
# Initialize start and end seconds to 0
start = 0
end = 0
# Flag to keep track of end of file.
# When audio reaches its end, flag is set to 1 and we break
flag = 0
# Iterate from 0 to end of the file,
# with increment = interval
for i in range(0, 2 * n, interval):
# During first iteration,
# start is 0, end is the interval
if i == 0:
start = 0
end = interval
# All other iterations,
# start is the previous end - overlap
# end becomes end + interval
else:
start = end - overlap
end = start + interval
# When end becomes greater than the file length,
# end is set to the file length
# flag is set to 1 to indicate break.
if end >= n:
end = n
flag = 1
# Storing audio file from the defined start to end
chunk = audio[start:end]
# Filename / Path to store the sliced audio
filename = str(chunk_count)+'chunk'+str(counter)+'.wav'
# Store the sliced audio file to the defined path
chunk.export(filename, format ="wav")
# Print information about the current chunk
print(str(chunk_count)+str(counter)+". Start = "
+str(start)+" end = "+str(end))
# Increment counter for the next chunk
counter = counter + 1
AUDIO_FILE = filename
# Initialize the recognizer
r = sr.Recognizer()
# Traverse the audio file and listen to the audio
with sr.AudioFile(AUDIO_FILE) as source:
audio_listened = r.listen(source)
# Try to recognize the listened audio
# And catch expections.
try:
rec = r.recognize_google(audio_listened)
# If recognized, write into the file.
fh.write(rec+" ")
# If google could not understand the audio
except sr.UnknownValueError:
print("Empty Value")
# If the results cannot be requested from Google.
# Probably an internet connection error.
except sr.RequestError as e:
print("Could not request results.")
# Check for flag.
# If flag is 1, end of the whole audio reached.
# Close the file and break.
fh.close()
Traceback (последний вызов был последним): файл "C: \ Users \ zach.blair \ Downloads \ speechRecognition \ Newпапка \ speechRecognition3.py ", строка 17, в файле audio = AudioSegment.from_file (имя файла, формат =" wav ") Файл" C: \ Users \ zach.blair \ AppData \ Local \ Programs \ Python \ Python37-32 \ lib \site-packages \ pydub \ audio_segment.py ", строка 704, в from_file p.returncode, p_err)) pydub.exceptions.CouldntDecodeError: Не удалось декодировать.ffmpeg вернул код ошибки: 1
Вывод из ffmpeg / avlib:
b "ffmpeg версия N-95027-g8c90bb8ebb Copyright (c) 2000-2019 разработчики FFmpeg \ r \ n, созданные с помощью gcc9.2.1 (GCC) Конфигурация 20190918 \ r \ n: --enable-gpl --enable-version3 --enable-sdl2 --enable-fontconfig --enable-gnutls --enable-iconv --enable-libass -enable-libdav1d --enable-libbluray --enable-libfreetype --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopus --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libtheora --enable-libtwolame --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libzimg --enable-lzma --enable-zlib --enable-gmp --enable-libvidstab --enable-libvorbis --enable-libvo-amrwbenc --enable-libmysofa --enable-libspeex --enable-libxvid --enable-libaom --enable-libmfx --enable-ffnvcodec --enable-cuvid --enable-d3d11va --enable-nvenc --enable-nvdec --enable-dxva2 --enable-avisynth --enable-libopenmpt --enable-amf \ r \ n libavutil 56. 35.100 / 56. 35.100 \ r \ n libavcodec 58. 58.101 / 58. 58.101 \ r \ n libavformat 58. 33.100 / 5833.100 \ r \ n libavdevice 58. 9.100 / 58. 9.100 \ r \ n libavfilter 7. 58.102 / 7. 58.102 \ r \ n libswscale 5. 6.100 / 5. 6.100 \ r \ n libswresample 3. 6.100 / 3. 6.100\ r \ n libpostproc 55. 6.100 / 55. 6.100 \ r \ nГаданное расположение каналов для входного потока # 0.0: моно \ r \ nВход # 0, wav, из '2a.wav.wav': \ r \ n Продолжительность: 00: 09: 52.95, битрейт: 64 кбит / с \ r \ n Поток # 0: 0: аудио: pcm_mulaw ([7] [0] [0] [0] / 0x0007), 8000 Гц, моно, s16, 64 кб/ s \ r \ nОтображение потока: \ r \ n Поток # 0: 0 -> # 0: 0 (pcm_mulaw (собственный) -> pcm_s8 (собственный)) \ r \ nНажмите [q], чтобы остановить, [?] для помощи\ r \ n [wav @ 0000024307974400] Кодек pcm_s8 не поддерживается в формате WAVE \ r \ nНе удалось записать заголовок для выходного файла # 0 (неверные параметры кодека?): функция не реализована \ r \ nОшибка инициализации выходного потока 0: 0 -\ r \ nКонверсия не удалась! \ r \ n "