Update app.py

app.py

@@ -321,19 +321,19 @@ with gr.Blocks() as yav_ui:
     with gr.Row():
         with gr.Column():
             with gr.Tab("Youtube", id=1):
-                ysz = gr.Dropdown(label="Model Size", choices=wispher_models, value='base')
+                ysz = gr.Dropdown(label="Model Size", choices=wispher_models , value='base')
                 yinput_nos = gr.Number(label="Number of Speakers", placeholder="2")
                 yinput_sn = gr.Textbox(label="Name of the Speakers (ordered by the time they speak and separated by comma)", placeholder="If Speaker 1 is first to speak followed by Speaker 2 then -> Speaker 1, Speaker 2")
                 yinput = gr.Textbox(label="Youtube Link", placeholder="https://www.youtube.com/watch?v=GECcjrYHH8w")
                 ybutton_transcribe = gr.Button("Transcribe", show_progress=True, scroll_to_output=True)
             with gr.Tab("Video", id=2):
-                vsz = gr.Dropdown(label="Model Size", choices=wispher_models, value='base')
+                vsz = gr.Dropdown(label="Model Size", choices=wispher_models)
                 vinput_nos = gr.Number(label="Number of Speakers", placeholder="2")
                 vinput_sn = gr.Textbox(label="Name of the Speakers (ordered by the time they speak and separated by comma)", placeholder="If Speaker 1 is first to speak followed by Speaker 2 then -> Speaker 1, Speaker 2")
                 vinput = gr.Video(label="Video")
                 vbutton_transcribe = gr.Button("Transcribe", show_progress=True, scroll_to_output=True)
             with gr.Tab("Audio", id=3):
-                asz = gr.Dropdown(label="Model Size", choices=wispher_models, value='base')
+                asz = gr.Dropdown(label="Model Size", choices=wispher_models , value='base')
                 ainput_nos = gr.Number(label="Number of Speakers", placeholder="2")
                 ainput_sn = gr.Textbox(label="Name of the Speakers (ordered by the time they speak and separated by comma)", placeholder="If Speaker 1 is first to speak followed by Speaker 2 then -> Speaker 1, Speaker 2")
                 ainput = gr.Audio(label="Audio", type="filepath")
@@ -345,17 +345,17 @@ with gr.Blocks() as yav_ui:
                 output_json = gr.JSON(label="Transcribed JSON")
     ybutton_transcribe.click(
                 fn=YoutubeTranscribe,
-                inputs=[yinput_nos,yinput_sn,yinput],
+                inputs=[yinput_nos,yinput_sn,yinput, ysz],
                 outputs=[output_textbox,output_json]
             )
     abutton_transcribe.click(
                 fn=AudioTranscribe,
-                inputs=[ainput_nos,ainput_sn,ainput],
+                inputs=[ainput_nos,ainput_sn,ainput], asz,
                 outputs=[output_textbox,output_json]
             )
     vbutton_transcribe.click(
                 fn=VideoTranscribe,
-                inputs=[vinput_nos,vinput_sn,vinput],
+                inputs=[vinput_nos,vinput_sn,vinput, vsz],
                 outputs=[output_textbox,output_json]
             )
 yav_ui.launch(debug=True)