slow.py

import sys
import os
import speech_recognition as sr
from tqdm import tqdm

with open("/var/www/html/speech_to_text/api-key.json") as f:
    GOOGLE_CLOUD_SPEECH_CREDENTIALS = f.read()

try:
    folderName = sys.argv[1]
    folderName = folderName + '/'
    with open("logs", "w") as f:
        f.write('got foldername ' + folderName)
    print("foldername " + folderName)
except IndexError:
    print("Usage:\npython3 slow.py folder_name")
    with open("logs", "w") as f:
        f.write("caught exception")
    sys.exit(1)


r = sr.Recognizer()

files = sorted(os.listdir(folderName))
all_text = []
print(files)

try:
    for f in tqdm(files):
        print('for f in tqdm ' + folderName + f)
        name = folderName + f
        print('name ' + name)
        # Load audio file
        with sr.AudioFile(name) as source:
            print('inside source')
            audio = r.record(source)
            print('done source')
            # Transcribe audio file

        print('credentials ' + GOOGLE_CLOUD_SPEECH_CREDENTIALS)
        text = r.recognize_google_cloud(audio, credentials_json=GOOGLE_CLOUD_SPEECH_CREDENTIALS)
        print('took credentials')
        all_text.append(text)
except Exception, e:
    print('exception in text=r.recognize ' + str(e))

transcript = ""
for i, t in enumerate(all_text):
    total_seconds = i * 30
    # Cool shortcut from:
    # https://stackoverflow.com/questions/775049/python-time-seconds-to-hms
    # to get hours, minutes and seconds
    m, s = divmod(total_seconds, 60)
    h, m = divmod(m, 60)

    # Format time as h:m:s - 30 seconds of text
    transcript = transcript + "{:0>2d}:{:0>2d}:{:0>2d} {}\n".format(h, m, s, t)
    print(transcript)
print(transcript)

with open("transcript.txt", "w") as f:
    f.write(transcript)