Update app.py

app.py

@@ -137,6 +137,15 @@ def get_transcribe_state(segments):
 
 @spaces.GPU(duration=60)
 def transcribe(seed, audio_path):
+    # first, create your aligner
+    aligner = WhisperxAlignModel()
+
+    # then load the ASR+alignment combo
+    transcribe_model = WhisperxModel(
+        model_name="large.en",   # or "base.en", "small.en", etc.
+        align_model=aligner
+    )
+        
     if transcribe_model is None:
         raise gr.Error("Transcription model not loaded")
     seed_everything(seed)
@@ -454,18 +463,6 @@ def update_demo(mode, smart_transcript, edit_word_mode, transcript, edit_from_wo
 
 def get_app():
     with gr.Blocks() as app:
-        with gr.Row():
-            with gr.Column(scale=2):
-                load_models_btn = gr.Button(value="Load models")
-            with gr.Column(scale=5):
-                with gr.Accordion("Select models", open=False) as models_selector:
-                    with gr.Row():
-                        voicecraft_model_choice = gr.Radio(label="VoiceCraft model", value="830M_TTSEnhanced",
-                                                        choices=["330M", "830M", "330M_TTSEnhanced", "830M_TTSEnhanced"])
-                        whisper_backend_choice = gr.Radio(label="Whisper backend", value="whisperX", choices=["whisperX", "whisper"])
-                        whisper_model_choice = gr.Radio(label="Whisper model", value="base.en",
-                                                        choices=[None, "base.en", "small.en", "medium.en", "large"])
-                        align_model_choice = gr.Radio(label="Forced alignment model", value="whisperX", choices=["whisperX", None])
 
         with gr.Row():
             with gr.Column(scale=2):