siennathesane · July 22, 2017 07:34
diff --git a/main.py b/main.py
 from __future__ import print_function

 import os
 import subprocess
 import sys
 import threading
 import time

 import requests
 from flask import Flask, request, redirect, url_for, flash
 from flask_session import Session
 from google.cloud import speech
 from google.cloud import storage
 from google.cloud.speech import enums
 from google.cloud.speech import types
 from summa import summarizer
 from werkzeug.utils import secure_filename

 FFMPEG = os.path.join(os.path.dirname(__file__), "ffmpeg.exe")

 app = Flask(__name__)
 UPLOAD_FOLDER = '.'
 ALLOWED_EXTENSIONS = set(['avi', 'mp4', 'mkv'])
 SESSION_TYPE = 'filesystem'

 app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
 app.secret_key = os.urandom(8)
 sess = Session(app)
 sess.init_app(app)


 def allowed_file(filename):
    return '.' in filename and \
           filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS


 @app.route('/', methods=['GET', 'POST'])
 def upload_file():
    if request.method == 'POST':
        # check if the post request has the file part
        if 'file' not in request.files:
            flash('No file part')
            return redirect(request.url)
        file = request.files['file']
        if file.filename == '':
            return redirect(request.url)
        if file and allowed_file(file.filename):
            filename = secure_filename(file.filename)
            file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
            process_file(filename)
            return redirect(url_for('upload_file',
                                    filename=filename))
    return '''
    <!doctype html>
    <title>Upload new File</title>
    <h1>Upload new File</h1>
    <form method=post enctype=multipart/form-data>
      <p><input type=file name=file>
         <input type=submit value=Upload>
    </form>
    '''


 def process_file(filename):
    print("Processing file {0}".format(filename), file=sys.stderr)
    now = time.time().hex()
    local_filename = "audio-{0}.flac".format(now)

    command = [FFMPEG, "-i", filename, "-ab", "160k", "-acodec", "flac", "-ac", "1", "-ar", "16000", "-vn",
               local_filename]

    subprocess.call(" ".join(command), shell=True)

    storage_client = storage.Client(project=os.getenv("PROJECT_ID"))
    bucket = storage_client.get_bucket(os.getenv("BUCKET_NAME"))
    blobber = bucket.blob(local_filename)
    blobber.upload_from_filename(local_filename)

    os.remove(local_filename)

    transcript_thread = threading.Thread(target=get_transcript, args=[local_filename])
    transcript_thread.start()
    return


 def get_transcript(uri):
    """Asynchronously transcribes the audio file specified by the gcs_uri."""

    client = speech.SpeechClient()

    audio = types.RecognitionAudio(uri='gs://{0}/{1}'.format(os.getenv("BUCKET_NAME"), uri))
    config = types.RecognitionConfig(
        encoding=enums.RecognitionConfig.AudioEncoding.FLAC,
        sample_rate_hertz=16000,
        language_code='en-US')

    operation = client.long_running_recognize(config, audio)

    retry_count = 100
    while retry_count > 0 and not operation.done():
        print("Waiting for {0} retries".format(retry_count), file=sys.stderr)
        retry_count -= 1
        time.sleep(10)

    if not operation.done():
        print('Operation not complete and retry limit reached.')
        return

    res = operation.result().results

    transcribed = ". ".join(extract_transcript(x) for x in res)
    try:
        print(summarizer.summarize(transcribed), file=sys.stderr)
    except ZeroDivisionError:
        return


 def extract_transcript(x):
    # run it through the grammar twice in case there are multiple choices.
    return ask_lt(x.alternatives[0].transcript)


 def ask_lt(s):
    s = s.strip()  # Believe this removes all whitespace from left and right
    # Need to trim both left and right for elipses
    while s[:3] == '...':
        s = s[3:]
    while s[-3:] == '...':
        s = s[:-3]
    params = {"text": s, "language": "en-US"}
    resp = requests.get("http://127.0.0.1:8081/v2/check", params=params).json()
    try:
        # basically, if this is empty, it will throw an exception we can catch, and then break the loop.
        mistake = resp["matches"][0]
        _ = mistake["message"]  # throws KeyError if no match
    except (KeyError, IndexError):
        return s
    else:
        local_context = mistake["context"]
        original_string = s
        print(local_context, file=sys.stderr)
        fixed_string = ''.join([
            original_string[:local_context["offset"]],
            mistake["replacements"][0]["value"],
            original_string[local_context["length"] + local_context["offset"]:],
        ])
        return ask_lt(fixed_string)


 if __name__ == '__main__':
    app.run(debug=True)
    # app.run(debug=False, port=int(os.getenv("PORT")), host="0.0.0.0")
	from __future__ import print_function

	import os
	import subprocess
	import sys
	import threading
	import time

	import requests
	from flask import Flask, request, redirect, url_for, flash
	from flask_session import Session
	from google.cloud import speech
	from google.cloud import storage
	from google.cloud.speech import enums
	from google.cloud.speech import types
	from summa import summarizer
	from werkzeug.utils import secure_filename

	FFMPEG = os.path.join(os.path.dirname(__file__), "ffmpeg.exe")

	app = Flask(__name__)
	UPLOAD_FOLDER = '.'
	ALLOWED_EXTENSIONS = set(['avi', 'mp4', 'mkv'])
	SESSION_TYPE = 'filesystem'

	app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
	app.secret_key = os.urandom(8)
	sess = Session(app)
	sess.init_app(app)


	def allowed_file(filename):
	return '.' in filename and \
	filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS


	@app.route('/', methods=['GET', 'POST'])
	def upload_file():
	if request.method == 'POST':
	# check if the post request has the file part
	if 'file' not in request.files:
	flash('No file part')
	return redirect(request.url)
	file = request.files['file']
	if file.filename == '':
	return redirect(request.url)
	if file and allowed_file(file.filename):
	filename = secure_filename(file.filename)
	file.save(os.path.join(app.config['UPLOAD_FOLDER'], filename))
	process_file(filename)
	return redirect(url_for('upload_file',
	filename=filename))
	return '''
	<!doctype html>
	<title>Upload new File</title>
	<h1>Upload new File</h1>
	<form method=post enctype=multipart/form-data>
	<p><input type=file name=file>
	<input type=submit value=Upload>
	</form>
	'''


	def process_file(filename):
	print("Processing file {0}".format(filename), file=sys.stderr)
	now = time.time().hex()
	local_filename = "audio-{0}.flac".format(now)

	command = [FFMPEG, "-i", filename, "-ab", "160k", "-acodec", "flac", "-ac", "1", "-ar", "16000", "-vn",
	local_filename]

	subprocess.call(" ".join(command), shell=True)

	storage_client = storage.Client(project=os.getenv("PROJECT_ID"))
	bucket = storage_client.get_bucket(os.getenv("BUCKET_NAME"))
	blobber = bucket.blob(local_filename)
	blobber.upload_from_filename(local_filename)

	os.remove(local_filename)

	transcript_thread = threading.Thread(target=get_transcript, args=[local_filename])
	transcript_thread.start()
	return


	def get_transcript(uri):
	"""Asynchronously transcribes the audio file specified by the gcs_uri."""

	client = speech.SpeechClient()

	audio = types.RecognitionAudio(uri='gs://{0}/{1}'.format(os.getenv("BUCKET_NAME"), uri))
	config = types.RecognitionConfig(
	encoding=enums.RecognitionConfig.AudioEncoding.FLAC,
	sample_rate_hertz=16000,
	language_code='en-US')

	operation = client.long_running_recognize(config, audio)

	retry_count = 100
	while retry_count > 0 and not operation.done():
	print("Waiting for {0} retries".format(retry_count), file=sys.stderr)
	retry_count -= 1
	time.sleep(10)

	if not operation.done():
	print('Operation not complete and retry limit reached.')
	return

	res = operation.result().results

	transcribed = ". ".join(extract_transcript(x) for x in res)
	try:
	print(summarizer.summarize(transcribed), file=sys.stderr)
	except ZeroDivisionError:
	return


	def extract_transcript(x):
	# run it through the grammar twice in case there are multiple choices.
	return ask_lt(x.alternatives[0].transcript)


	def ask_lt(s):
	s = s.strip() # Believe this removes all whitespace from left and right
	# Need to trim both left and right for elipses
	while s[:3] == '...':
	s = s[3:]
	while s[-3:] == '...':
	s = s[:-3]
	params = {"text": s, "language": "en-US"}
	resp = requests.get("http://127.0.0.1:8081/v2/check", params=params).json()
	try:
	# basically, if this is empty, it will throw an exception we can catch, and then break the loop.
	mistake = resp["matches"][0]
	_ = mistake["message"] # throws KeyError if no match
	except (KeyError, IndexError):
	return s
	else:
	local_context = mistake["context"]
	original_string = s
	print(local_context, file=sys.stderr)
	fixed_string = ''.join([
	original_string[:local_context["offset"]],
	mistake["replacements"][0]["value"],
	original_string[local_context["length"] + local_context["offset"]:],
	])
	return ask_lt(fixed_string)


	if __name__ == '__main__':
	app.run(debug=True)
	# app.run(debug=False, port=int(os.getenv("PORT")), host="0.0.0.0")