Speech model selection (GoogleCloudPlatform#1361)

dizcology · Jon Wayne Parrott · commit f6d7fe44ff92 · 2018-02-26T10:36:28.000-08:00
* add transcribe_model_selection

* add transcribe_model_selection_test

* flake
diff --git a/speech/cloud-client/resources/Google_Gnome.wav b/speech/cloud-client/resources/Google_Gnome.wav
diff --git a/speech/cloud-client/transcribe_model_selection.py b/speech/cloud-client/transcribe_model_selection.py
@@ -0,0 +1,102 @@
+#!/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 that demonstrates how to select the model
+used for speech recognition.
+
+Example usage:
+    python transcribe_model_selection.py \
+        resources/Google_Gnome.wav --model video
+    python transcribe_model_selection.py \
+        gs://cloud-samples-tests/speech/Google_Gnome.wav --model video
+"""
+
+import argparse
+
+
+# [START speech_transcribe_model_selection]
+def transcribe_model_selection(speech_file, model):
+    """Transcribe the given audio file synchronously with
+    the selected model."""
+    from google.cloud import speech_v1p1beta1 as speech
+    client = speech.SpeechClient()
+
+    with open(speech_file, 'rb') as audio_file:
+        content = audio_file.read()
+
+    audio = speech.types.RecognitionAudio(content=content)
+
+    config = speech.types.RecognitionConfig(
+        encoding=speech.enums.RecognitionConfig.AudioEncoding.LINEAR16,
+        sample_rate_hertz=16000,
+        language_code='en-US',
+        model=model)
+
+    response = client.recognize(config, audio)
+
+    for i, result in enumerate(response.results):
+        alternative = result.alternatives[0]
+        print('-' * 20)
+        print('First alternative of result {}'.format(i))
+        print('Transcript: {}'.format(alternative.transcript))
+# [END speech_transcribe_model_selection]
+
+
+# [START speech_transcribe_model_selection_gcs]
+def transcribe_model_selection_gcs(gcs_uri, model):
+    """Transcribe the given audio file asynchronously with
+    the selected model."""
+    from google.cloud import speech_v1p1beta1 as speech
+    client = speech.SpeechClient()
+
+    audio = speech.types.RecognitionAudio(uri=gcs_uri)
+
+    config = speech.types.RecognitionConfig(
+        encoding=speech.enums.RecognitionConfig.AudioEncoding.LINEAR16,
+        sample_rate_hertz=16000,
+        language_code='en-US',
+        model=model)
+
+    operation = client.long_running_recognize(config, audio)
+
+    print('Waiting for operation to complete...')
+    response = operation.result(timeout=90)
+
+    for i, result in enumerate(response.results):
+        alternative = result.alternatives[0]
+        print('-' * 20)
+        print('First alternative of result {}'.format(i))
+        print('Transcript: {}'.format(alternative.transcript))
+# [END speech_transcribe_model_selection_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')
+    parser.add_argument(
+        '--model', help='The speech recognition model to use',
+        choices=['command_and_search', 'phone_call', 'video', 'default'],
+        default='default')
+
+    args = parser.parse_args()
+
+    if args.path.startswith('gs://'):
+        transcribe_model_selection_gcs(args.path, args.model)
+    else:
+        transcribe_model_selection(args.path, args.model)
diff --git a/speech/cloud-client/transcribe_model_selection_test.py b/speech/cloud-client/transcribe_model_selection_test.py
@@ -0,0 +1,35 @@
+# Copyright 2016, Google, Inc.
+# 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.
+
+import os
+import re
+
+import transcribe_model_selection
+
+RESOURCES = os.path.join(os.path.dirname(__file__), 'resources')
+
+
+def test_transcribe_model_selection_file(capsys):
+    transcribe_model_selection.transcribe_model_selection(
+        os.path.join(RESOURCES, 'Google_Gnome.wav'), 'video')
+    out, err = capsys.readouterr()
+
+    assert re.search(r'the weather outside is sunny', out, re.DOTALL | re.I)
+
+
+def test_transcribe_model_selection_gcs(capsys):
+    transcribe_model_selection.transcribe_model_selection_gcs(
+        'gs://cloud-samples-tests/speech/Google_Gnome.wav', 'video')
+    out, err = capsys.readouterr()
+
+    assert re.search(r'the weather outside is sunny', out, re.DOTALL | re.I)
