def test_recognize(self):
        # Setup Expected Response
        expected_response = {}
        expected_response = cloud_speech_pb2.RecognizeResponse(
            **expected_response)

        # Mock the API response
        channel = ChannelStub(responses=[expected_response])
        patch = mock.patch("google.api_core.grpc_helpers.create_channel")
        with patch as create_channel:
            create_channel.return_value = channel
            client = speech_v1p1beta1.SpeechClient()

        # Setup Request
        encoding = enums.RecognitionConfig.AudioEncoding.FLAC
        sample_rate_hertz = 44100
        language_code = "en-US"
        config = {
            "encoding": encoding,
            "sample_rate_hertz": sample_rate_hertz,
            "language_code": language_code,
        }
        uri = "gs://bucket_name/file_name.flac"
        audio = {"uri": uri}

        response = client.recognize(config, audio)
        assert expected_response == response

        assert len(channel.requests) == 1
        expected_request = cloud_speech_pb2.RecognizeRequest(config=config,
                                                             audio=audio)
        actual_request = channel.requests[0][1]
        assert expected_request == actual_request
    def test_streaming_recognize(self):
        # Setup Expected Response
        expected_response = {}
        expected_response = cloud_speech_pb2.StreamingRecognizeResponse(
            **expected_response)

        # Mock the API response
        channel = ChannelStub(responses=[iter([expected_response])])
        patch = mock.patch("google.api_core.grpc_helpers.create_channel")
        with patch as create_channel:
            create_channel.return_value = channel
            client = speech_v1p1beta1.SpeechClient()

        # Setup Request
        request = {}
        request = cloud_speech_pb2.StreamingRecognizeRequest(**request)
        requests = [request]

        response = client.streaming_recognize(requests)
        resources = list(response)
        assert len(resources) == 1
        assert expected_response == resources[0]

        assert len(channel.requests) == 1
        actual_requests = channel.requests[0][1]
        assert len(actual_requests) == 1
        actual_request = list(actual_requests)[0]
        assert request == actual_request
    def test_recognize(self):
        # Setup Expected Response
        expected_response = {}
        expected_response = cloud_speech_pb2.RecognizeResponse(
            **expected_response)

        # Mock the API response
        channel = ChannelStub(responses=[expected_response])
        client = speech_v1p1beta1.SpeechClient(channel=channel)

        # Setup Request
        encoding = enums.RecognitionConfig.AudioEncoding.FLAC
        sample_rate_hertz = 44100
        language_code = 'en-US'
        config = {
            'encoding': encoding,
            'sample_rate_hertz': sample_rate_hertz,
            'language_code': language_code
        }
        uri = 'gs://bucket_name/file_name.flac'
        audio = {'uri': uri}

        response = client.recognize(config, audio)
        assert expected_response == response

        assert len(channel.requests) == 1
        expected_request = cloud_speech_pb2.RecognizeRequest(
            config=config, audio=audio)
        actual_request = channel.requests[0][1]
        assert expected_request == actual_request
    def test_long_running_recognize_exception(self):
        # Setup Response
        error = status_pb2.Status()
        operation = operations_pb2.Operation(
            name="operations/test_long_running_recognize_exception", done=True)
        operation.error.CopyFrom(error)

        # Mock the API response
        channel = ChannelStub(responses=[operation])
        patch = mock.patch("google.api_core.grpc_helpers.create_channel")
        with patch as create_channel:
            create_channel.return_value = channel
            client = speech_v1p1beta1.SpeechClient()

        # Setup Request
        encoding = enums.RecognitionConfig.AudioEncoding.FLAC
        sample_rate_hertz = 44100
        language_code = "en-US"
        config = {
            "encoding": encoding,
            "sample_rate_hertz": sample_rate_hertz,
            "language_code": language_code,
        }
        uri = "gs://bucket_name/file_name.flac"
        audio = {"uri": uri}

        response = client.long_running_recognize(config, audio)
        exception = response.exception()
        assert exception.errors[0] == error
    def test_streaming_recognize(self):
        # Setup Expected Response
        expected_response = {}
        expected_response = cloud_speech_pb2.StreamingRecognizeResponse(
            **expected_response)

        # Mock the API response
        channel = ChannelStub(responses=[iter([expected_response])])
        client = speech_v1p1beta1.SpeechClient(channel=channel)

        # Setup Request
        request = {}
        request = cloud_speech_pb2.StreamingRecognizeRequest(**request)
        requests = [request]

        response = client.streaming_recognize(requests)
        resources = list(response)
        assert len(resources) == 1
        assert expected_response == resources[0]

        assert len(channel.requests) == 1
        actual_requests = channel.requests[0][1]
        assert len(actual_requests) == 1
        actual_request = list(actual_requests)[0]
        assert request == actual_request
    def test_long_running_recognize_exception(self):
        # Setup Response
        error = status_pb2.Status()
        operation = operations_pb2.Operation(
            name='operations/test_long_running_recognize_exception', done=True)
        operation.error.CopyFrom(error)

        # Mock the API response
        channel = ChannelStub(responses=[operation])
        client = speech_v1p1beta1.SpeechClient(channel=channel)

        # Setup Request
        encoding = enums.RecognitionConfig.AudioEncoding.FLAC
        sample_rate_hertz = 44100
        language_code = 'en-US'
        config = {
            'encoding': encoding,
            'sample_rate_hertz': sample_rate_hertz,
            'language_code': language_code
        }
        uri = 'gs://bucket_name/file_name.flac'
        audio = {'uri': uri}

        response = client.long_running_recognize(config, audio)
        exception = response.exception()
        assert exception.errors[0] == error
    def test_streaming_recognize_exception(self):
        # Mock the API response
        channel = ChannelStub(responses=[CustomException()])
        client = speech_v1p1beta1.SpeechClient(channel=channel)

        # Setup request
        request = {}

        request = cloud_speech_pb2.StreamingRecognizeRequest(**request)
        requests = [request]

        with pytest.raises(CustomException):
            client.streaming_recognize(requests)
    def test_streaming_recognize_exception(self):
        # Mock the API response
        channel = ChannelStub(responses=[CustomException()])
        patch = mock.patch("google.api_core.grpc_helpers.create_channel")
        with patch as create_channel:
            create_channel.return_value = channel
            client = speech_v1p1beta1.SpeechClient()

        # Setup request
        request = {}

        request = cloud_speech_pb2.StreamingRecognizeRequest(**request)
        requests = [request]

        with pytest.raises(CustomException):
            client.streaming_recognize(requests)
Ejemplo n.º 9
0
def google_transcribe(audio_file_name):

    file_name = filepath + audio_file_name

    bucket_name = bucketname
    source_file_name = filepath + audio_file_name
    destination_blob_name = audio_file_name

    upload_blob(bucket_name, source_file_name, destination_blob_name)

    gcs_uri = 'gs://' + bucketname + '/' + audio_file_name
    transcript = ''

    client = speech_client.SpeechClient()
    first_lang = 'hi-IN'
    second_lang = 'en'
    audio = speech.RecognitionAudio(uri=gcs_uri)

    config = speech.RecognitionConfig(
        encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
        sample_rate_hertz=8000,
        language_code=first_lang,
        audio_channel_count=1,
        enable_separate_recognition_per_channel=False,
        max_alternatives=6,
    )

    operation = client.long_running_recognize(config, audio)
    response = operation.result(timeout=10000)

    confidence = 0

    num = 0

    for result in response.results:
        con = 0
        tran = ''
        for alternative in result.alternatives:
            if (alternative.confidence > con):
                con = alternative.confidence
                tran = alternative.transcript

        transcript += tran
        confidence = con

    return transcript, confidence
    def test_recognize_exception(self):
        # Mock the API response
        channel = ChannelStub(responses=[CustomException()])
        client = speech_v1p1beta1.SpeechClient(channel=channel)

        # Setup request
        encoding = enums.RecognitionConfig.AudioEncoding.FLAC
        sample_rate_hertz = 44100
        language_code = 'en-US'
        config = {
            'encoding': encoding,
            'sample_rate_hertz': sample_rate_hertz,
            'language_code': language_code
        }
        uri = 'gs://bucket_name/file_name.flac'
        audio = {'uri': uri}

        with pytest.raises(CustomException):
            client.recognize(config, audio)
    def test_recognize_exception(self):
        # Mock the API response
        channel = ChannelStub(responses=[CustomException()])
        patch = mock.patch("google.api_core.grpc_helpers.create_channel")
        with patch as create_channel:
            create_channel.return_value = channel
            client = speech_v1p1beta1.SpeechClient()

        # Setup request
        encoding = enums.RecognitionConfig.AudioEncoding.FLAC
        sample_rate_hertz = 44100
        language_code = "en-US"
        config = {
            "encoding": encoding,
            "sample_rate_hertz": sample_rate_hertz,
            "language_code": language_code,
        }
        uri = "gs://bucket_name/file_name.flac"
        audio = {"uri": uri}

        with pytest.raises(CustomException):
            client.recognize(config, audio)
    def test_long_running_recognize(self):
        # Setup Expected Response
        expected_response = {}
        expected_response = cloud_speech_pb2.LongRunningRecognizeResponse(
            **expected_response)
        operation = operations_pb2.Operation(
            name='operations/test_long_running_recognize', done=True)
        operation.response.Pack(expected_response)

        # Mock the API response
        channel = ChannelStub(responses=[operation])
        patch = mock.patch('google.api_core.grpc_helpers.create_channel')
        with patch as create_channel:
            create_channel.return_value = channel
            client = speech_v1p1beta1.SpeechClient()

        # Setup Request
        encoding = enums.RecognitionConfig.AudioEncoding.FLAC
        sample_rate_hertz = 44100
        language_code = 'en-US'
        config = {
            'encoding': encoding,
            'sample_rate_hertz': sample_rate_hertz,
            'language_code': language_code
        }
        uri = 'gs://bucket_name/file_name.flac'
        audio = {'uri': uri}

        response = client.long_running_recognize(config, audio)
        result = response.result()
        assert expected_response == result

        assert len(channel.requests) == 1
        expected_request = cloud_speech_pb2.LongRunningRecognizeRequest(
            config=config, audio=audio)
        actual_request = channel.requests[0][1]
        assert expected_request == actual_request