Add timestamps to show_all output in recognize_google_cloud

Uberi · Dec 5, 2017 · 6f61f6b · 6f61f6b
1 parent 6d0adb6
commit 6f61f6b
Show file tree

Hide file tree

Showing 2 changed files with 6 additions and 4 deletions.
diff --git a/examples/threaded_workers.py b/examples/threaded_workers.py
@@ -34,6 +34,7 @@ def recognize_worker():
 
         audio_queue.task_done()  # mark the audio processing job as completed in the queue
 
+
 # start a new thread to recognize audio, while this thread focuses on listening
 recognize_thread = Thread(target=recognize_worker)
 recognize_thread.daemon = True

diff --git a/speech_recognition/__init__.py b/speech_recognition/__init__.py
@@ -962,10 +962,11 @@ def recognize_google_cloud(self, audio_data, credentials_json=None, language="en
         except ImportError:
             raise RequestError("missing google-api-python-client module: ensure that google-api-python-client is set up correctly.")
 
-        if preferred_phrases is None:
-            speech_config = {"encoding": "FLAC", "sampleRateHertz": audio_data.sample_rate, "languageCode": language}
-        else:
-            speech_config = {"encoding": "FLAC", "sampleRateHertz": audio_data.sample_rate, "languageCode": language, "speechContext": {"phrases": preferred_phrases}}
+        speech_config = {"encoding": "FLAC", "sampleRateHertz": audio_data.sample_rate, "languageCode": language}
+        if preferred_phrases is not None:
+            speech_config["speechContext"] = {"phrases": preferred_phrases}
+        if show_all:
+            speech_config["enableWordTimeOffsets"] = True  # some useful extra options for when we want all the output
         request = speech_service.speech().recognize(body={"audio": {"content": base64.b64encode(flac_data).decode("utf8")}, "config": speech_config})
 
         try: