Update app.py

app.py

@@ -90,19 +90,16 @@ engine = initialize_engine(DEFAULT_TTS_MODEL_PATH, DEFAULT_AUDIO_TOKENIZER_PATH)
 os.environ["PROCESSED_RESULTS"] = f"{os.getcwd()}/proprocess_results"
 
 @spaces.GPU
-def tts_from_text(text, voice_choice):
-    _, output = text_to_speech(engine, text, voice_preset=voice_choice)
+def tts_from_text(text):
+    _, output = text_to_speech(engine, text)
     return output
 
 def speak_to_me(session_id, evt: gr.EventData):
     detail = getattr(evt, "data", None) or getattr(evt, "_data", {}) or {}
 
     current_text = detail.get("text", "")
-    current_choice = detail.get("choice", "")
 
-    print(current_choice)
-
-    output = tts_from_text(current_text, current_choice)
+    output = tts_from_text(current_text)
 
     if session_id is None:
         session_id = uuid.uuid4().hex
@@ -764,7 +761,7 @@ with gr.Blocks(css=css) as demo:
             with gr.Column():
 
                 image_input = gr.Image(label="Reference Image", type="filepath", height=512)
-                audio_input = ExtendedAudio(label="Input Audio", type="filepath", options=["Cleon", "Cleo"], show_download_button=True)
+                audio_input = ExtendedAudio(label="Input Audio", type="filepath", options=["EMPTY"], show_download_button=True)
 
 
             with gr.Column():