speech: canonical sample for speechcontext ga of classes [(#2756)](#2756)

* speech: canonical sample for speechcontext ga of classes

* speech: fixing adaptation per Noah's comments

Author: czahedi

speech/snippets/requirements.txt

@@ -1 +1 @@
-google-cloud-speech==1.2.0
+google-cloud-speech==1.3.1

speech/snippets/transcribe_context_classes.py

@@ -0,0 +1,47 @@
+# 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
+#
+#      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.
+
+
+def transcribe_context_classes(storage_uri):
+    """Provides "hints" to the speech recognizer to
+    favor specific classes of words in the results."""
+    # [START speech_context_classes]
+    from google.cloud import speech
+    client = speech.SpeechClient()
+
+    # storage_uri = 'gs://YOUR_BUCKET_ID/path/to/your/file.wav'
+    audio = speech.types.RecognitionAudio(uri=storage_uri)
+
+    # SpeechContext: to configure your speech_context see:
+    # https://cloud.google.com/speech-to-text/docs/reference/rpc/google.cloud.speech.v1#speechcontext
+    # Full list of supported phrases (class tokens) here:
+    # https://cloud.google.com/speech-to-text/docs/class-tokens
+    speech_context = speech.types.SpeechContext(phrases=['$TIME'])
+
+    # RecognitionConfig: to configure your encoding and sample_rate_hertz, see:
+    # https://cloud.google.com/speech-to-text/docs/reference/rpc/google.cloud.speech.v1#recognitionconfig
+    config = speech.types.RecognitionConfig(
+        encoding=speech.enums.RecognitionConfig.AudioEncoding.LINEAR16,
+        sample_rate_hertz=8000,
+        language_code='en-US',
+        speech_contexts=[speech_context])
+
+    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_context_classes]

speech/snippets/transcribe_context_classes_test.py

@@ -0,0 +1,22 @@
+# 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
+#
+#    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 transcribe_context_classes
+
+
+def test_transcribe_context_classes(capsys):
+    transcribe_context_classes.transcribe_context_classes(
+        'gs://cloud-samples-data/speech/commercial_mono.wav')
+    out, _ = capsys.readouterr()
+
+    assert 'First alternative of result ' in out