update ws.py

diff --git a/ws.py b/ws.py
index 7dd80279535356016fe3e90d19bde4291e10f987..428cb356267cdeec0665604a2492606057378cb0 100644 (file)
--- a/ws.py
+++ b/ws.py
@@ -12,39 +12,61 @@ from google.cloud import speech
 client = speech.SpeechClient()
 
 
+# config = speech.RecognitionConfig(
+#     encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
+#     sample_rate_hertz=16000,
+#     language_code="en-US",
+# )
+
+# streaming_config = speech.StreamingRecognitionConfig(config=config)
+
+# def transcribe(stream):
+
+#     requests = (
+#         speech.StreamingRecognizeRequest(audio_content=chunk) for chunk in stream
+#     )
+
+#     # Detects speech in the audio file
+#     responses = client.streaming_recognize(
+#             config=config,
+#             requests=requests
+#     )
+
+#     for response in responses:
+#             # Once the transcription has settled, the first result will contain the
+#             # is_final result. The other results will be for subsequent portions of
+#             # the audio.
+#             for result in response.results:
+#                 print("Finished: {}".format(result.is_final))
+#                 print("Stability: {}".format(result.stability))
+#                 alternatives = result.alternatives
+#                 # The alternatives are ordered from most likely to least.
+#                 for alternative in alternatives:
+#                     print("Confidence: {}".format(alternative.confidence))
+#                     print(u"Transcript: {}".format(alternative.transcript))
+
+
+speechtotext_client = speech.SpeechClient()
+
 config = speech.RecognitionConfig(
     encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
-    sample_rate_hertz=16000,
+    sample_rate_hertz=44100,
     language_code="en-US",
 )
 
-streaming_config = speech.StreamingRecognitionConfig(config=config)
-
-def transcribe(stream):
+# Transcribe an audio file.
+def transcribe(content):
+    input(content)
+    input(type(content))
 
-    requests = (
-        speech.StreamingRecognizeRequest(audio_content=chunk) for chunk in stream
-    )
+    content = speech.RecognitionAudio(content=content)
 
     # Detects speech in the audio file
-    responses = client.streaming_recognize(
-            config=config,
-            requests=requests
-    )
-
-    for response in responses:
-            # Once the transcription has settled, the first result will contain the
-            # is_final result. The other results will be for subsequent portions of
-            # the audio.
-            for result in response.results:
-                print("Finished: {}".format(result.is_final))
-                print("Stability: {}".format(result.stability))
-                alternatives = result.alternatives
-                # The alternatives are ordered from most likely to least.
-                for alternative in alternatives:
-                    print("Confidence: {}".format(alternative.confidence))
-                    print(u"Transcript: {}".format(alternative.transcript))
+    response = speechtotext_client.recognize(config=config, audio=content)
+    input(f"Response: {response}")
 
+    for result in response.results:
+        return result.alternatives[0].transcript
 
 
 async def session(websocket, path):
@@ -58,10 +80,12 @@ async def session(websocket, path):
 
         buf.append(chunk)
 
-    transcribe(buf)
+    input(f"Buffer sample:" {buf[0]})
+    audio = b"".join(buf)
+
+    transcribe(audio)
 
 
 start_server = websockets.serve(session, "localhost", 8080)
 asyncio.get_event_loop().run_until_complete(start_server)
 asyncio.get_event_loop().run_forever()
-