I am in need to able to translate custom audio bytes which I can get from any source and translate the voice into the language I need (currently Hindi). I have been trying to pass custom audio bytes using following code in Python:
import azure.cognitiveservices.speech as speechsdk
from azure.cognitiveservices.speech.audio import AudioStreamFormat, PullAudioInputStream, PullAudioInputStreamCallback, AudioConfig, PushAudioInputStream
speech_key, service_region = "key", "region"
channels = 1
bitsPerSample = 16
samplesPerSecond = 16000
audioFormat = AudioStreamFormat(samplesPerSecond, bitsPerSample, channels)
class CustomPullAudioInputStreamCallback(PullAudioInputStreamCallback):
def __init__(self):
return super(CustomPullAudioInputStreamCallback, self).__init__()
def read(self, file_bytes):
print (len(file_bytes))
return len(file_bytes)
def close(self):
return super(CustomPullAudioInputStreamCallback, self).close()
class CustomPushAudioInputStream(PushAudioInputStream):
def write(self, file_bytes):
print (type(file_bytes))
return super(CustomPushAudioInputStream, self).write(file_bytes)
def close():
return super(CustomPushAudioInputStream, self).close()
translation_config = speechsdk.translation.SpeechTranslationConfig(subscription=speech_key, region=service_region)
fromLanguage = 'en-US'
toLanguage = 'hi'
translation_config.speech_recognition_language = fromLanguage
translation_config.add_target_language(toLanguage)
translation_config.voice_name = "hi-IN-Kalpana-Apollo"
pull_audio_input_stream_callback = CustomPullAudioInputStreamCallback()
# pull_audio_input_stream = PullAudioInputStream(pull_audio_input_stream_callback, audioFormat)
# custom_pull_audio_input_stream = CustomPushAudioInputStream(audioFormat)
audio_config = AudioConfig(use_default_microphone=False, stream=pull_audio_input_stream_callback)
recognizer = speechsdk.translation.TranslationRecognizer(translation_config=translation_config,
audio_config=audio_config)
def synthesis_callback(evt):
size = len(evt.result.audio)
print('AUDIO SYNTHESIZED: {} byte(s) {}'.format(size, '(COMPLETED)' if size == 0 else ''))
if size > 0:
t_sound_file = open("translated_output.wav", "wb+")
t_sound_file.write(evt.result.audio)
t_sound_file.close()
recognizer.stop_continuous_recognition_async()
def recognized_complete(evt):
if evt.result.reason == speechsdk.ResultReason.TranslatedSpeech:
print("RECOGNIZED '{}': {}".format(fromLanguage, result.text))
print("TRANSLATED into {}: {}".format(toLanguage, result.translations['hi']))
elif evt.result.reason == speechsdk.ResultReason.RecognizedSpeech:
print("RECOGNIZED: {} (text could not be translated)".format(result.text))
elif evt.result.reason == speechsdk.ResultReason.NoMatch:
print("NOMATCH: Speech could not be recognized: {}".format(result.no_match_details))
elif evt.reason == speechsdk.ResultReason.Canceled:
print("CANCELED: Reason={}".format(result.cancellation_details.reason))
if result.cancellation_details.reason == speechsdk.CancellationReason.Error:
print("CANCELED: ErrorDetails={}".format(result.cancellation_details.error_details))
def receiving_bytes(audio_bytes):
# audio_bytes contain bytes of audio to be translated
recognizer.synthesizing.connect(synthesis_callback)
recognizer.recognized.connect(recognized_complete)
pull_audio_input_stream_callback.read(audio_bytes)
recognizer.start_continuous_recognition_async()
receiving_bytes(audio_bytes)
Output: Error: AttributeError: 'PullAudioInputStreamCallback' object has no attribute '_impl'
Packages and their versions:
Python 3.6.3 azure-cognitiveservices-speech 1.11.0
File Translation can be successfully performed but I do not want to save files for each chunk of bytes I receive.
Can you me pass custom audio bytes to the Azure Speech Translation Service and get the result in Python? If yes then how?
I got the solution to the problem by myself. I think it works with PullAudioInputStream too. But it worked for me using PushAudioInputStream. You don't need to create custom classes it would work like the following:
import azure.cognitiveservices.speech as speechsdk
from azure.cognitiveservices.speech.audio import AudioStreamFormat, PullAudioInputStream, PullAudioInputStreamCallback, AudioConfig, PushAudioInputStream
from threading import Thread, Event
speech_key, service_region = "key", "region"
channels = 1
bitsPerSample = 16
samplesPerSecond = 16000
audioFormat = AudioStreamFormat(samplesPerSecond, bitsPerSample, channels)
translation_config = speechsdk.translation.SpeechTranslationConfig(subscription=speech_key, region=service_region)
fromLanguage = 'en-US'
toLanguage = 'hi'
translation_config.speech_recognition_language = fromLanguage
translation_config.add_target_language(toLanguage)
translation_config.voice_name = "hi-IN-Kalpana-Apollo"
# Remove Custom classes as they are not needed.
custom_push_stream = speechsdk.audio.PushAudioInputStream(stream_format=audioFormat)
audio_config = AudioConfig(stream=custom_push_stream)
recognizer = speechsdk.translation.TranslationRecognizer(translation_config=translation_config, audio_config=audio_config)
# Create an event
synthesis_done = Event()
def synthesis_callback(evt):
size = len(evt.result.audio)
print('AUDIO SYNTHESIZED: {} byte(s) {}'.format(size, '(COMPLETED)' if size == 0 else ''))
if size > 0:
t_sound_file = open("translated_output.wav", "wb+")
t_sound_file.write(evt.result.audio)
t_sound_file.close()
# Setting the event
synthesis_done.set()
def recognized_complete(evt):
if evt.result.reason == speechsdk.ResultReason.TranslatedSpeech:
print("RECOGNIZED '{}': {}".format(fromLanguage, result.text))
print("TRANSLATED into {}: {}".format(toLanguage, result.translations['hi']))
elif evt.result.reason == speechsdk.ResultReason.RecognizedSpeech:
print("RECOGNIZED: {} (text could not be translated)".format(result.text))
elif evt.result.reason == speechsdk.ResultReason.NoMatch:
print("NOMATCH: Speech could not be recognized: {}".format(result.no_match_details))
elif evt.reason == speechsdk.ResultReason.Canceled:
print("CANCELED: Reason={}".format(result.cancellation_details.reason))
if result.cancellation_details.reason == speechsdk.CancellationReason.Error:
print("CANCELED: ErrorDetails={}".format(result.cancellation_details.error_details))
recognizer.synthesizing.connect(synthesis_callback)
recognizer.recognized.connect(recognized_complete)
# Read and get data from an audio file
open_audio_file = open("speech_wav_audio.wav", 'rb')
file_bytes = open_audio_file.read()
# Write the bytes to the stream
custom_push_stream.write(file_bytes)
custom_push_stream.close()
# Start the recognition
recognizer.start_continuous_recognition()
# Waiting for the event to complete
synthesis_done.wait()
# Once the event gets completed you can call Stop recognition
recognizer.stop_continuous_recognition()
I have used Event from thread since start_continuous_recognition starts in a different thread and you won't get data from callback events if you don't use threading. synthesis_done.wait will solve this problem by waiting for the event to complete and only then will call the stop_continuous_recognition. Once you obtain the audio bytes you can do whatever you wish in the synthesis_callback. I have simplified the example and took bytes from a wav file.