I'm not too familiar with python, apologies if this is too trivial question
I have a script that get an audio file from an Url, I need to convert the file from .ogg type to .wav
Then I want to pass the converted and loaded file, to a function that has as argument a filepath string.
Below is my code:
import os
import pydub
import glob
import time
from io import BytesIO
import pandas as pd
from urllib.request import Request, urlopen
import urllib.error
import azure.cognitiveservices.speech as speechsdk
import time
#%%
audio_file = "https = url.whatever.com.co/audio_file.ogg"
req = Request(audio_file)
try: response = urlopen(req).read()
except urllib.error.URLError as e:
print(e.reason)
sound = pydub.AudioSegment.from_ogg(BytesIO(response))
sound_wav = sound.export(format = "wav")
speech_key, service_region = "XXXXXXXXXXXXXXXX", "eastus"
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
speech_config.speech_recognition_language="es-ES"
audio_filename = r"C:\some_file_path\3AC3844337F7E5CEAE95.wav"
#audio_config = speechsdk.audio.AudioConfig(sound_wav)
audio_config = speechsdk.audio.AudioConfig(audio_filename = audio_filename)
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
done = False
def stop_cb(evt):
"""callback that stops continuous recognition upon receiving an event `evt`"""
print('CLOSING on {}'.format(evt))
speech_recognizer.stop_continuous_recognition()
global done
done = True
all_results = []
def handle_final_result(evt):
all_results.append(evt.result.text)
speech_recognizer.recognized.connect(handle_final_result)
# Connect callbacks to the events fired by the speech recognizer
speech_recognizer.recognized.connect(lambda evt: print('RECOGNIZED: {}'.format(evt)))
# stop continuous recognition on either session stopped or canceled events
speech_recognizer.session_stopped.connect(stop_cb)
speech_recognizer.canceled.connect(stop_cb)
# Start continuous speech recognition
speech_recognizer.start_continuous_recognition()
while not done:
time.sleep(.5)
print("Printing all results:")
print(all_results)
When I run my code with this line:
audio_config = speechsdk.audio.AudioConfig(audio_filename = audio_filename)
It works correct...
However when I run it with this line:
audio_config = speechsdk.audio.AudioConfig(sound_wav)
I get this error:
ValueError: use_default_microphone must be a bool, is "tempfile._TemporaryFileWrapper object at 0x0000020EC4297668"
The error message you got suggests that sound_wav is a temporary filename. Then, as seen in the documentation, it looks like audio_config = speechsdk.audio.AudioConfig(filename = sound_wav) is what you need.
As you used audio_filename as a parameter, it could happen that a different version uses that different name. You can using that instead.
Related
I have used this code from geeksforgeeks (https://www.geeksforgeeks.org/language-translator-using-google-api-in-python/), I am trying to run it and it runs without any error, and it prints out:
Speak 'hello' to initiate the Translation !
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
but when i say "hello" it does not recognize it and do not start listening for translation.
I have imported all the modules, tried updating every one of them, and also Im using a macbook m1 pro.
And heres the code:
import speech_recognition as spr
from googletrans import Translator
from gtts import gTTS
import os
# Creating Recogniser() class object
recog1 = spr.Recognizer()
# Creating microphone instance
mc = spr.Microphone()
# Capture Voice
with mc as source:
print("Speak 'hello' to initiate the Translation !")
print("~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~")
recog1.adjust_for_ambient_noise(source, duration=0.2)
audio = recog1.listen(source)
MyText = recog1.recognize_google(audio)
MyText = MyText.lower()
# Here initialising the recorder with
# hello, whatever after that hello it
# will recognise it.
if 'hello' in MyText:
# Translator method for translation
translator = Translator()
# short form of english in which
# you will speak
from_lang = 'en'
# In which we want to convert, short
# form of hindi
to_lang = 'hi'
with mc as source:
print("Speak a stentence...")
recog1.adjust_for_ambient_noise(source, duration=0.2)
# Storing the speech into audio variable
audio = recog1.listen(source)
# Using recognize.google() method to
# convert audio into text
get_sentence = recog1.recognize_google(audio)
# Using try and except block to improve
# its efficiency.
try:
# Printing Speech which need to
# be translated.
print("Phase to be Translated :"+ get_sentence)
# Using translate() method which requires
# three arguments, 1st the sentence which
# needs to be translated 2nd source language
# and 3rd to which we need to translate in
text_to_translate = translator.translate(get_sentence,
src= from_lang,
dest= to_lang)
# Storing the translated text in text
# variable
text = text_to_translate.text
# Using Google-Text-to-Speech ie, gTTS() method
# to speak the translated text into the
# destination language which is stored in to_lang.
# Also, we have given 3rd argument as False because
# by default it speaks very slowly
speak = gTTS(text=text, lang=to_lang, slow= False)
# Using save() method to save the translated
# speech in capture_voice.mp3
speak.save("captured_voice.mp3")
# Using OS module to run the translated voice.
os.system("start captured_voice.mp3")
# Here we are using except block for UnknownValue
# and Request Error and printing the same to
# provide better service to the user.
except spr.UnknownValueError:
print("Unable to Understand the Input")
except spr.RequestError as e:
print("Unable to provide Required Output".format(e))
from gtts import gTTS
from io import BytesIO
from pygame import mixer
import time
def speak():
mp3_fp = BytesIO()
tts = gTTS('KGF is a Great movie to watch', lang='en')
tts.write_to_fp(mp3_fp)
tts.save("Audio.mp3")
return mp3_fp
mixer.init()
sound = speak()
sound.seek(0)
mixer.music.load(sound, "mp3")
mixer.music.play()
So I was writing a python script using telebot and got an error
A request to the Telegram API was unsuccessful. Error code: 400.
Description: Bad Request: file must be non-empty
I have tried different methods from many forums, but nothing helps
import telebot
import random
import time
token = #token here
bot = telebot.TeleBot(token)
shit = ["C:\\Users\\glebc\\Documents\\source(bot)\\3wZ3.gif.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\65216814_456719028224290_7745639790787166208_n.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\doc_2022-03-10_16-41-49.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\doc_2022-03-10_16-42-04.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\doc_2022-03-10_16-42-39.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\giphy.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_0080.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_0835.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_1362.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_4698.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_4962.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_6359.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_7497.MOV", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_7909.MOV", "C:\\Users\\glebc\\Documents\\source(bot)\\IMG_9540.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\mp4.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\video.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\комочек тьмы.mp4", "C:\\Users\\glebc\\Documents\\source(bot)\\кот.mp4"]
video = open(shit[random.randint(0, len(shit)-1)], 'rb')
#bot.message_handler(commands=['start'])
def start_message(message):
bot.send_message(message.chat.id, 'hello message 1')
#bot.message_handler(commands=['haha'])
def haha_message(message):
while True:
bot.send_video(message.chat.id, vidos)
time.sleep(3600) #1 hour
#bot.message_handler(commands=['hehe'])
def shit_message(message):
bot.send_video(message.chat.id, vidos)
bot.infinity_polling()
Also i dont understand error cause i dont close file only open
Problem can be because you open file only once and you never close it and open again.
When it reads then it move special pointer which shows where to read next time. When it reads to the end of file then this pointer is moved to the end of file and when it tries to read again then it trires to read from the end of file and there is nothing to read and it may say that you have empty file.
After reading you may have to use vidoe.seek(0) to move pointer to the beginnig of file.
Or you should close and open it again. And this can be even more useful because at this moment you select random file only once and later it would use always the same path. You should use random inside loop.
#bot.message_handler(commands=['haha'])
def haha_message(message):
while True:
video = open( random.choice(shit), 'rb')
bot.send_video(message.chat.id, video)
video.close()
time.sleep(3600) # 1 hour
and the same in other functions
#bot.message_handler(commands=['hehe'])
def shit_message(message):
video = open( random.choice(shit), 'rb')
bot.send_video(message.chat.id, video)
video.close()
BTW:
telegram may has some methods to execute tasks periodically.
For example module python-telegram-bot has telegram.ext.jobqueue for this.
Full working code
For tests I set logging.DEBUG to see all error messages.
Normally telebot catchs all errors and hides them.
I also used with open() as video so it automatically closes file.
import os
import random
import logging
import telebot
# display errors
telebot.logger.setLevel(logging.DEBUG)
TOKEN = os.getenv('TELEGRAM_TOKEN')
bot = telebot.TeleBot(TOKEN)
all_videos = [
"C:\\Users\\glebc\\Documents\\source(bot)\\3wZ3.gif.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\65216814_456719028224290_7745639790787166208_n.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\doc_2022-03-10_16-41-49.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\doc_2022-03-10_16-42-04.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\doc_2022-03-10_16-42-39.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\giphy.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_0080.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_0835.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_1362.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_4698.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_4962.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_6359.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_7497.MOV",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_7909.MOV",
"C:\\Users\\glebc\\Documents\\source(bot)\\IMG_9540.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\mp4.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\video.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\комочек тьмы.mp4",
"C:\\Users\\glebc\\Documents\\source(bot)\\кот.mp4"
]
#bot.message_handler(commands=['start'])
def start_message(message):
bot.send_message(message.chat.id, 'hello message 1')
#bot.message_handler(commands=['haha'])
def haha_message(message):
while True:
with open(random.choice(all_videos), 'rb') as video:
bot.send_video(message.chat.id, video)
time.sleep(3600) # 1 hour
#bot.message_handler(commands=['hehe'])
def shit_message(message):
with open(random.choice(all_videos), 'rb') as video:
bot.send_video(message.chat.id, video)
bot.infinity_polling()
I am using the ArtifactsClient from azure-synapse-artifacts library and trying to upload a new Workspace Package. When doing this manually through the UI it works and my Provisioning State is set to "Succeeded". When I try to do the same though the SDK I won't get the "Succeeded", and hence cannot use the library in my Spark Pool.
Here is the code I'm using:
from time import sleep
from azure.identity import DefaultAzureCredential
from azure.synapse.artifacts import ArtifactsClient
client = ArtifactsClient(credential=DefaultAzureCredential(), endpoint="https://mysynapseworkspace.dev.azuresynapse.net")
ws = client.workspace.get()
library_client = client.library
wheel_name = 'dalib.whl'
poller = library_client.begin_create(wheel_name)
while not poller.done():
print(poller.status())
sleep(1)
whl = open('C:\\path\\to\\wheelfile\\wheel_tester-0.0.1-py3-none-any.whl', 'rb')
library_client.append(library_name=wheel_name, content=whl)
whl.close()
Ok so I solved this.
It seems that after you've created the library and called the append() method you also have to use begin_flush() in order to set the provisioning state to "succeeded". However, this is not mentioned in any documentation I have found. If anyone has the same problem that I had I post the working code below:
from time import sleep
from azure.core.exceptions import ResourceExistsError
from azure.identity import DefaultAzureCredential
from azure.synapse.artifacts import ArtifactsClient
credential = DefaultAzureCredential()
client = ArtifactsClient(credential=credential, endpoint="https://synws.dev.azuresynapse.net")
ws = client.workspace.get()
library_client = client.library
wheel_name = 'wheel_tester-0.0.1-py3-none-any.whl'
whl = open(f'C:\\path\\to\\wheelfile\\{wheel_name}', 'rb')
try:
print('creating library')
poller = library_client.begin_create(wheel_name)
while not poller.done():
print(poller.status())
sleep(1)
print(poller.status())
print(poller.result())
except ResourceExistsError as ree:
print('resource already exists.')
print('appending content')
library_client.append(library_name=wheel_name, content=whl)
print('flushing library')
lro_poller = library_client.begin_flush(library_name=wheel_name)
while not lro_poller.done():
print(lro_poller.status())
sleep(1)
print(lro_poller.status())
print(lro_poller.result())
whl.close()
I'm using Microsoft Azure's speech-to-text API and it's working well but the output is cumbersome and I'd like to clean it up so that only the recognized speech is displayed.
this is what the output looks like
The python snippet that azure provides is:
try:
import azure.cognitiveservices.speech as speechsdk
import sys
sys.exit(1)
speech_key, service_region = "***", "***"
weatherfilename = os.path.join(
os.path.dirname(__file__),
'orf_audio_2',
'716_anton.wav')
# def speech_recognize_once_from_file():
"""performs one-shot speech recognition with input from an audio file"""
# <SpeechRecognitionWithFile>
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
audio_config = speechsdk.audio.AudioConfig(filename=weatherfilename)
# Creates a speech recognizer using a file as audio input.
# The default language is "en-us".
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
start_continuous_recognition() instead.
result = speech_recognizer.recognize_once()
# Check the result
if result.reason == speechsdk.ResultReason.RecognizedSpeech:
print("Recognized: {}".format(result.text))
elif result.reason == speechsdk.ResultReason.NoMatch:
print("No speech could be recognized: {}".format(result.no_match_details))
elif result.reason == speechsdk.ResultReason.Canceled:
cancellation_details = result.cancellation_details
print("Speech Recognition canceled: {}".format(cancellation_details.reason))
if cancellation_details.reason == speechsdk.CancellationReason.Error:
print("Error details: {}".format(cancellation_details.error_details))
# </SpeechRecognitionWithFile>
result.text in the sample code is the simplest output of recognized speech.
My test with default microphone:
Please refer to below fragment of code which works for me.
import azure.cognitiveservices.speech as speechsdk
import time
# Creates an instance of a speech config with specified subscription key and service region.
# Replace with your own subscription key and service region (e.g., "westus").
speech_key, service_region = "***", "***"
weatherfilename = "D:\\whatstheweatherlike.wav"
speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
audio_config = speechsdk.audio.AudioConfig(filename=weatherfilename)
# Creates a recognizer with the given settings
speech_recognizer = speechsdk.SpeechRecognizer(speech_config=speech_config, audio_config=audio_config)
speech_recognizer.session_started.connect(lambda evt: print('SESSION STARTED: {}'.format(evt)))
speech_recognizer.session_stopped.connect(lambda evt: print('\nSESSION STOPPED {}'.format(evt)))
speech_recognizer.recognized.connect(lambda evt: print('\n{}'.format(evt.result.text)))
# print('Say a few words\n\n')
speech_recognizer.start_continuous_recognition()
time.sleep(10)
speech_recognizer.stop_continuous_recognition()
speech_recognizer.session_started.disconnect_all()
speech_recognizer.recognized.disconnect_all()
speech_recognizer.session_stopped.disconnect_all()
And the output looks like:
I have searched and tried to implement solutions suggested here:
Errno 13 Permission denied: 'file.mp3' Python
Error while re-opening sound file in python
But there doesn't seem to be any good solutions to this. Here is my code, can anyone tell me what I am doing wrong here:
#!/usr/bin/env python3
# Requires PyAudio and PySpeech.
import time, os
import speech_recognition as sr
from gtts import gTTS
import pygame as pg
import mutagen.mp3
#Find out what input sound device is default (use if you have issues with microphone)
#import pyaudio
#sdev= pyaudio.pa.get_default_input_device()
def play_music(sound_file, volume=0.8):
'''
stream music with mixer.music module in a blocking manner
this will stream the sound from disk while playing
'''
# set up the mixer, this will set it up according to your sound file
mp3 = mutagen.mp3.MP3(sound_file)
pg.mixer.init(frequency=mp3.info.sample_rate)
pg.mixer.music.set_volume(volume)
try:
pg.mixer.music.load(sound_file)
print("HoBo Sound file {} loaded!".format(sound_file))
except pg.error:
print("HoBo Sound file {} not found! ({})".format(sound_file, pg.get_error()))
return
pg.mixer.music.play()
while pg.mixer.music.get_busy() == True:
continue
pg.mixer.quit()
sound_file.close()
def speak(audioString):
print(audioString)
tts = gTTS(text=audioString, lang='en')
tts.save("audio.mp3")
# pick a mp3 file in folder or give full path
sound_file = "audio.mp3"
# optional volume 0 to 1.0
volume = 0.6
play_music(sound_file, volume)
def audioIn():
# Record Audio from Microphone
r = sr.Recognizer()
with sr.Microphone() as source:
print("Say something!")
audio = r.listen(source)
# Google Speech Recognition
try:
# for testing purposes, we're just using the default API key
# to use another API key, use `r.recognize_google(audio, key="GOOGLE_SPEECH_RECOGNITION_API_KEY")`
# instead of `r.recognize_google(audio)`
data = r.recognize_google(audio)
print("You said: ", data)
except sr.UnknownValueError:
print("Google Speech Recognition could not understand audio")
except sr.RequestError as e:
print("Could not request results from Google Speech Recognition service; {0}".format(e))
return data
def hobo(data):
if "how are you" in data:
speak("I am fine")
if "what time is it" in data:
speak(time.ctime())
if "where is" in data:
data = data.split(" ")
location = data[2]
speak("Hold on Sir, I will show you where " + location + " is.")
os.system("chromium-browser https://www.google.nl/maps/place/" + location + "/&")
# Starts the program
#time.sleep(2)
speak("Testing")
while(data != "stop"):
data = audioIn()
hobo(data)
else:
quit
So I found the fix in one of the original threads I already went over. The fix was to implement a delete() function like so:
def delete():
time.sleep(2)
pg.mixer.init()
pg.mixer.music.load("somefilehere.mp3")
os.remove("audio.mp3")
and changing the play_music() function so it includes the delete() function in the end (and I removed the sound_file.close() statement of course).
Follow below method
import time
from gtts import gTTS
import pygame
def Text_to_speech():
Message = "hey there"
speech = gTTS(text=Message)
speech.save('textToSpeech.mp3')
pygame.mixer.init()
pygame.mixer.music.load("textToSpeech.mp3")
pygame.mixer.music.play()
time.sleep(3)
pygame.mixer.music.unload()