wip

Author: ks6088ts

apps/99_streamlit_examples/pages/13_Azure_AI_Speech.py

@@ -1,3 +1,4 @@
+import time
 from os import getenv
 
 import azure.cognitiveservices.speech as speechsdk
@@ -59,13 +60,55 @@ def get_speech_config():
 
 
 def from_mic():
-    speech_recognizer = speechsdk.SpeechRecognizer(
+    conversation_transcriber = speechsdk.transcription.ConversationTranscriber(
         speech_config=get_speech_config(),
     )
 
-    print("Speak into your microphone.")
-    speech_recognition_result = speech_recognizer.recognize_once_async().get()
-    print(speech_recognition_result.text)
+    transcribing_stop = False
+
+    def stop_cb(evt: speechsdk.SessionEventArgs):
+        # """callback that signals to stop continuous recognition upon receiving an event `evt`"""
+        print(f"CLOSING on {evt}")
+        nonlocal transcribing_stop
+        transcribing_stop = True
+
+    # Connect callbacks to the events fired by the conversation transcriber
+    conversation_transcriber.transcribed.connect(conversation_transcriber_transcribed_cb)
+    conversation_transcriber.session_started.connect(conversation_transcriber_session_started_cb)
+    conversation_transcriber.session_stopped.connect(conversation_transcriber_session_stopped_cb)
+    conversation_transcriber.canceled.connect(conversation_transcriber_recognition_canceled_cb)
+    # stop transcribing on either session stopped or canceled events
+    conversation_transcriber.session_stopped.connect(stop_cb)
+    conversation_transcriber.canceled.connect(stop_cb)
+
+    conversation_transcriber.start_transcribing_async()
+
+    # Waits for completion.
+    while not transcribing_stop:
+        time.sleep(0.5)
+
+    conversation_transcriber.stop_transcribing_async()
+
+
+def conversation_transcriber_recognition_canceled_cb(evt: speechsdk.SessionEventArgs):
+    print("Canceled event")
+
+
+def conversation_transcriber_session_stopped_cb(evt: speechsdk.SessionEventArgs):
+    print("SessionStopped event")
+
+
+def conversation_transcriber_transcribed_cb(evt: speechsdk.SpeechRecognitionEventArgs):
+    print("TRANSCRIBED:")
+    if evt.result.reason == speechsdk.ResultReason.RecognizedSpeech:
+        print(f"\tText={evt.result.text}")
+        print(f"\tSpeaker ID={evt.result.speaker_id}")
+    elif evt.result.reason == speechsdk.ResultReason.NoMatch:
+        print(f"\tNOMATCH: Speech could not be TRANSCRIBED: {evt.result.no_match_details}")
+
+
+def conversation_transcriber_session_started_cb(evt: speechsdk.SessionEventArgs):
+    print("SessionStarted event")
 
 
 st.title("Azure AI Speech Services")