Add code snippet for auto-detect language feature. (GoogleCloudPlatform#10923)

mnadev · web-flow · commit b4ce5d51aea2 · 2023-11-16T11:51:54.000-05:00
docs(samples): Add code snippet for chirp auto-detect language feature
diff --git a/speech/snippets/transcribe_chirp_auto_detect_language.py b/speech/snippets/transcribe_chirp_auto_detect_language.py
@@ -0,0 +1,77 @@
+# Copyright 2023 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 argparse
+
+# [START speech_transcribe_chirp_auto_detect_language]
+
+from google.api_core.client_options import ClientOptions
+from google.cloud.speech_v2 import SpeechClient
+from google.cloud.speech_v2.types import cloud_speech
+
+
+def transcribe_chirp_auto_detect_language(
+    project_id: str,
+    audio_file: str,
+    region: str = "us-central1",
+) -> cloud_speech.RecognizeResponse:
+    """Transcribe an audio file and auto-detect spoken language using Chirp.
+
+    Please see https://cloud.google.com/speech-to-text/v2/docs/encoding for more
+    information on which audio encodings are supported.
+    """
+    # Instantiates a client
+    client = SpeechClient(
+        client_options=ClientOptions(
+            api_endpoint=f"{region}-speech.googleapis.com",
+        )
+    )
+
+    # Reads a file as bytes
+    with open(audio_file, "rb") as f:
+        content = f.read()
+
+    config = cloud_speech.RecognitionConfig(
+        auto_decoding_config=cloud_speech.AutoDetectDecodingConfig(),
+        language_codes=["auto"],  # Set language code to auto to detect language.
+        model="chirp",
+    )
+
+    request = cloud_speech.RecognizeRequest(
+        recognizer=f"projects/{project_id}/locations/{region}/recognizers/_",
+        config=config,
+        content=content,
+    )
+
+    # Transcribes the audio into text
+    response = client.recognize(request=request)
+
+    for result in response.results:
+        print(f"Transcript: {result.alternatives[0].transcript}")
+        print(f"Detected Language: {result.language_code}")
+
+    return response
+
+# [END speech_transcribe_chirp_auto_detect_language]
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description=__doc__, formatter_class=argparse.RawDescriptionHelpFormatter
+    )
+    parser.add_argument("project_id", help="GCP Project ID")
+    parser.add_argument("audio_file", help="Audio file to stream")
+    args = parser.parse_args()
+    transcribe_chirp_auto_detect_language(args.project_id, args.audio_file)
diff --git a/speech/snippets/transcribe_chirp_auto_detect_language_test.py b/speech/snippets/transcribe_chirp_auto_detect_language_test.py
@@ -0,0 +1,39 @@
+# Copyright 2023 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.
+
+import os
+import re
+
+from google.api_core.retry import Retry
+
+import transcribe_chirp_auto_detect_language
+
+_RESOURCES = os.path.join(os.path.dirname(__file__), "resources")
+
+
+@Retry()
+def test_transcribe_chirp() -> None:
+    project_id = os.getenv("GOOGLE_CLOUD_PROJECT")
+
+    response = transcribe_chirp_auto_detect_language.transcribe_chirp_auto_detect_language(
+        project_id, os.path.join(_RESOURCES, "audio.wav")
+    )
+
+    assert re.search(
+        r"how old is the Brooklyn Bridge",
+        response.results[0].alternatives[0].transcript,
+        re.DOTALL | re.I,
+    )
+
+    assert response.results[0].language_code == 'en'
