On the local server this Python app works perfectly, however, when I set up this Python app on my server where my site is hosted, index.html loads and that means Python is well set up, but when I click the Transcribe button, after as I select the language and .wav file, an error occurs:
Internal Server Error
The server encountered an internal error and was unable to complete your request. Either the server is overloaded or there is an error in the application.
Does anyone have any idea where the error is here and if it is not an error, how to overcome the server response.
from flask import Flask, render_template, request, redirect
import speech_recognition as sr
import requests
app = Flask(__name__)
def get_languages():
url = 'https://cloud.google.com/speech-to-text/docs/languages'
resp = requests.get(url)
start_text = ' <tbody class="list">\n'
end_text = ' </tbody>\n'
table = resp.text.split(start_text)[1].split(end_text)[0]
tr_start = ' <tr>\n'
sections = table.split(tr_start)[1:]
languages = []
for section in sections:
short = section.splitlines()[1].split('<td>')[1].split('<')[0]
long = section.splitlines()[0].split('<td>')[1].split('<')[0]
if len(languages) > 0:
# dupe check. For some reason the page has all
# languages twice
if languages[-1] != {'short': short, 'long': long}:
languages.append({'short': short, 'long': long})
else:
languages.append({'short': short, 'long': long})
print(f'FOUND {len(languages)} LANGUAGES')
return languages
language_list = get_languages()
@app.route("/", methods=["GET", "POST"])
def index():
transcript = ""
if request.method == "POST":
print("FORM DATA RECEIVED")
# set the language, use en-US by default
language = request.form.get('lang') or 'en-US'
print(f'SELECTED LANGUAGE: {language}')
if "file" not in request.files:
return redirect(request.url)
file = request.files["file"]
if file.filename == "":
return redirect(request.url)
if file:
recognizer = sr.Recognizer()
audioFile = sr.AudioFile(file)
with audioFile as source:
data = recognizer.record(source)
recognizer.adjust_for_ambient_noise(source)
# change the line below
transcript = recognizer.recognize_google(data, language=language)
return render_template('index.html', transcript=transcript, language_list=language_list)
if __name__ == "__main__":
app.run(debug=True, threaded=True)
log file
FOUND 137 LANGUAGES
FORM DATA RECEIVED
SELECTED LANGUAGE: en-US
FOUND 137 LANGUAGES
[2021-08-08 13:37:18,913] ERROR in app: Exception on / [POST]
Traceback (most recent call last):
File "/home/mysrv/virtualenv/transcriber/3.7/lib/python3.7/site-packages/flask/app.py", line 2070, in wsgi_app
response = self.full_dispatch_request()
File "/home/mysrv/virtualenv/transcriber/3.7/lib/python3.7/site-packages/flask/app.py", line 1515, in full_dispatch_request
rv = self.handle_user_exception(e)
File "/home/mysrv/virtualenv/transcriber/3.7/lib/python3.7/site-packages/flask/app.py", line 1513, in full_dispatch_request
rv = self.dispatch_request()
File "/home/mysrv/virtualenv/transcriber/3.7/lib/python3.7/site-packages/flask/app.py", line 1499, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**req.view_args)
File "app.py", line 58, in index
transcript = recognizer.recognize_google(data, language=language)
File "/home/mysrv/virtualenv/transcriber/3.7/lib/python3.7/site-packages/speech_recognition/__init__.py", line 828, in recognize_google
convert_width=2 # audio samples must be 16-bit
File "/home/mysrv/virtualenv/transcriber/3.7/lib/python3.7/site-packages/speech_recognition/__init__.py", line 445, in get_flac_data
flac_converter = get_flac_converter()
File "/home/mysrv/virtualenv/transcriber/3.7/lib/python3.7/site-packages/speech_recognition/__init__.py", line 1183, in get_flac_converter
flac_converter = shutil_which("flac") # check for installed version first
File "/home/mysrv/virtualenv/transcriber/3.7/lib/python3.7/site-packages/speech_recognition/__init__.py", line 1217, in shutil_which
for p in path.split(os.path.pathsep):
AttributeError: 'NoneType' object has no attribute 'split'
I cannot comment in the above discussion due to less points. No it is not due to server response time.
Did you try with
transcript = recognizer.recognize_google(data) instead