Upload app.py

app.py

@@ -231,8 +231,7 @@ def speech_to_text(video_file_path, selected_source_lang, whisper_model, num_spe
     # model = WhisperModel(whisper_model, device="cuda", compute_type="int8_float16")
     model = WhisperModel(whisper_model, compute_type="int8")
     time_start = time.time()
-    if(video_file_path == None):
-        raise ValueError("Error no video input")
+  
     print(video_file_path)
 
     try:
@@ -384,7 +383,6 @@ with demo:
                 upload = gr.inputs.Audio(source="upload", type="filepath", optional=True)
         with gr.Row():
             with gr.Column():
-                video_in.render()
                 with gr.Column():
                     gr.Markdown('''
                     ##### Here you can start the transcription process.
@@ -396,7 +394,7 @@ with demo:
                 number_speakers.render()
                 transcribe_btn = gr.Button("Transcribe audio and diarization")
                 transcribe_btn.click(speech_to_text, 
-                                     [video_in, selected_source_lang, selected_whisper_model, number_speakers], 
+                                     [upload, selected_source_lang, selected_whisper_model, number_speakers], 
                                      [transcription_df, system_info, download_transcript]
                                     )