speech_quickstart_beta.py

# Copyright 2020 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
#     https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# DO NOT EDIT! This is a generated sample ("Request",  "speech_quickstart_beta")

# To install the latest published package dependency, execute the following:
#   pip install google-cloud-speech

# sample-metadata
#   title: Quickstart Beta
#   description: Performs synchronous speech recognition on an audio file
#   usage: python3 samples/v1p1beta1/speech_quickstart_beta.py [--storage_uri "gs://cloud-samples-data/speech/brooklyn_bridge.mp3"]

# [START speech_quickstart_beta]
from google.cloud import speech_v1p1beta1 as speech


def sample_recognize(storage_uri):
    """
    Performs synchronous speech recognition on an audio file

    Args:
      storage_uri URI for audio file in Cloud Storage, e.g. gs://[BUCKET]/[FILE]
    """

    client = speech.SpeechClient()

    # storage_uri = 'gs://cloud-samples-data/speech/brooklyn_bridge.mp3'

    # The language of the supplied audio
    language_code = "en-US"

    # Sample rate in Hertz of the audio data sent
    sample_rate_hertz = 44100

    # Encoding of audio data sent. This sample sets this explicitly.
    # This field is optional for FLAC and WAV audio formats.
    encoding = speech.RecognitionConfig.AudioEncoding.MP3
    config = {
        "language_code": language_code,
        "sample_rate_hertz": sample_rate_hertz,
        "encoding": encoding,
    }
    audio = {"uri": storage_uri}

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

    for result in response.results:
        # First alternative is the most probable result
        alternative = result.alternatives[0]
        print("Transcript: {}".format(alternative.transcript))

    # [END speech_quickstart_beta]
    return response


def main():
    import argparse

    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--storage_uri",
        type=str,
        default="gs://cloud-samples-data/speech/brooklyn_bridge.mp3",
    )
    args = parser.parse_args()

    sample_recognize(args.storage_uri)


if __name__ == "__main__":
    main()