在Python中自定义音频输入字节到azure认知语音翻译服务中

问题描述 投票：0回答：1

我需要能够翻译自定义的音频字节，我可以从任何来源获得并将声音翻译成我需要的语言（目前是印地语）。我一直在尝试在Python中使用以下代码来传递自定义音频字节。

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' 对象没有属性'_impl'。

软件包及其版本。

Python 3.6.3azure-cognitiveservices-peech 1.11.0

文件翻译可以成功执行，但我不想为我收到的每个字节块保存文件。

你能让我将自定义音频字节传递给 Azure 语音翻译服务，并在 Python 中获得结果吗？如果是，那么怎么做？

python azure speech-recognition translation microsoft-cognitive
1个回答
0
投票

提供的示例代码使用回调作为AudioConfig的流参数，这似乎是不允许的。

这段代码应该可以正常工作，不会出现错误。

pull_audio_input_stream_callback = CustomPullAudioInputStreamCallback()
pull_audio_input_stream = PullAudioInputStream(pull_stream_callback=pull_audio_input_stream_callback, stream_format=audioFormat)

audio_config = AudioConfig(use_default_microphone=False, stream=pull_audio_input_stream)
0
投票

我自己找到了问题的解决方法。我想它也可以用PullAudioInputStream工作。但对我来说，使用PushAudioInputStream就可以了。你不需要创建自定义类，它的工作原理如下。

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()

我使用了Event from thread，因为 start_continuous_recognition 在不同的线程中启动，如果你不使用线程，你将无法从回调事件中获得数据。synthesis_done.wait 将通过等待事件完成来解决这个问题，然后才会调用 stop_continuous_recognition. 一旦你获得了音频字节，你就可以在下面的程序中为所欲为了。synthesis_callback. 我已经简化了这个例子，并从一个wav文件的字节。

最新问题
© www.soinside.com 2019 - 2024. All rights reserved.