mirror of
https://github.com/FAUSheppy/ths-speech
synced 2025-12-06 14:51:38 +01:00
87 lines
2.8 KiB
Python
87 lines
2.8 KiB
Python
#!/usr/bin/env python
|
|
|
|
# Copyright 2017 Google Inc. All Rights Reserved.
|
|
#
|
|
# 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
|
|
#
|
|
# http://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.
|
|
|
|
"""Google Cloud Speech API sample application using the REST API for async
|
|
batch processing.
|
|
|
|
Example usage:
|
|
python transcribe_async.py resources/audio.raw
|
|
python transcribe_async.py gs://cloud-samples-tests/speech/vr.flac
|
|
"""
|
|
|
|
import argparse
|
|
import io
|
|
from gcloud import storage
|
|
from google.cloud import speech
|
|
from google.cloud.speech import enums
|
|
from google.cloud.speech import types
|
|
|
|
|
|
# [START speech_transcribe_async]
|
|
def transcribe_file(speech_file):
|
|
url = upload_file(speech_file)
|
|
print(url)
|
|
return transcribe_gcs("gs://"+url)
|
|
|
|
def upload_file(filename):
|
|
bukket = "ths-speech-audio/"
|
|
client = storage.Client()
|
|
cb = client.get_bucket("ths-speech-audio")
|
|
blob = cb.blob(filename)
|
|
blob.upload_from_filename(filename)
|
|
return bukket + filename
|
|
|
|
def transcribe_gcs(gcs_uri):
|
|
"""Asynchronously transcribes the audio file specified by the gcs_uri."""
|
|
client = speech.SpeechClient()
|
|
|
|
audio = types.RecognitionAudio(uri=gcs_uri)
|
|
config = types.RecognitionConfig(
|
|
encoding=enums.RecognitionConfig.AudioEncoding.LINEAR16,
|
|
sample_rate_hertz=32000,
|
|
language_code='de-DE')
|
|
|
|
operation = client.long_running_recognize(config, audio)
|
|
|
|
print('Waiting for operation to complete...')
|
|
response = operation.result(timeout=900)
|
|
|
|
# Each result is for a consecutive portion of the audio. Iterate through
|
|
# them to get the transcripts for the entire audio file.
|
|
ret = ""
|
|
for result in response.results:
|
|
# The first alternative is the most likely one for this portion.
|
|
if len(result.alternatives) < 1:
|
|
continue
|
|
ret += result.alternatives[0].transcript
|
|
print(u'Transcript: {}'.format(result.alternatives[0].transcript))
|
|
print('Confidence: {}'.format(result.alternatives[0].confidence))
|
|
return ret
|
|
# [END speech_transcribe_async_gcs]
|
|
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser(
|
|
description=__doc__,
|
|
formatter_class=argparse.RawDescriptionHelpFormatter)
|
|
parser.add_argument(
|
|
'path', help='File or GCS path for audio file to be recognized')
|
|
args = parser.parse_args()
|
|
if args.path.startswith('gs://'):
|
|
transcribe_gcs(args.path)
|
|
else:
|
|
transcribe_file(args.path)
|