python - Python 中的 Azure 认知语音翻译服务的自定义音频输入字节

Question

我需要能够翻译可以从任何来源获得的自定义音频字节，并将语音翻译成我需要的语言(目前是印地语)。我一直在尝试使用 Python 中的以下代码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)

输出:错误:AttributeError:“PullAudioInputStreamCallback”对象没有属性“_impl”

软件包及其版本:

Python 3.6.3 azure 认知服务语音 1.11.0

文件翻译可以成功执行，但我不想为收到的每个字节 block 保存文件。

您能否将自定义音频字节传递到 Azure 语音翻译服务并在 Python 中获取结果？如果是的话怎么办？

Answer 1

我自己找到了解决问题的方法。我认为它也适用于 PullAudioInputStream。但它对我使用 PushAudioInputStream 有用。您不需要创建自定义类，它的工作方式如下:

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()

自从 start_continuous_recognition 在不同的线程中启动以来，我一直使用来自线程的事件，如果不使用线程，您将无法从回调事件中获取数据。 synthesis_done.wait 将通过等待事件完成来解决此问题，然后才会调用 stop_continuous_recognition。获得音频字节后，您可以在 synthesis_callback 中执行任何您想要的操作。我简化了示例并从 wav 文件中获取了字节。