add speech to text transcription

ws.py

@@ -11,59 +11,23 @@ from google.cloud import speech
 # Instantiates a client
 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(
     audio_channel_count=1,
     encoding=speech.RecognitionConfig.AudioEncoding.LINEAR16,
-    sample_rate_hertz=44100,
+    sample_rate_hertz=16000,
     language_code="en-US",
 )
 
 # Transcribe an audio file.
 def transcribe(content):
-    input(content)
-    input(type(content))
 
-    content = speech.RecognitionAudio(content=content)
+    print(len(content))
+    audio = speech.RecognitionAudio(content=content)
 
     # Detects speech in the audio file
-    response = speechtotext_client.recognize(config=config, audio=content)
+    response = speechtotext_client.recognize(config=config, audio=audio)
     input(f"Response: {response}")
 
     for result in response.results:
@@ -73,18 +37,21 @@ def transcribe(content):
 async def session(websocket, path):
     buf = []
 
-    while True:
-        chunk = await websocket.recv()
+    chunk = await websocket.recv()
+    input(type(chunk))
+    transcribe(chunk)
+     # while True:
+     #     chunk = await websocket.recv_frame()
 
-        if chunk == "stop":
-            break
+     #     if chunk == "stop":
+     #         break
 
-        buf.append(chunk)
+     #     buf.append(chunk)
 
-    input(f"Buffer sample: {buf[0]}")
-    audio = b"".join(buf)
+     # input(f"Buffer sample: {buf[0]}")
+     # audio = b"".join(buf)
 
-    transcribe(audio)
+     # transcribe(audio)
 
 
 start_server = websockets.serve(session, "localhost", 8080)