Update app.py

app.py

@@ -306,7 +306,7 @@ def speech_to_text(video_file_path, selected_source_lang, whisper_model, min_num
         save_path = "output/transcript_result.csv"
         df_results = pd.DataFrame(objects)
         df_results.to_csv(save_path)
-        return df_results, system_info, save_pathassuming
+        return df_results, system_info, save_path
     
     except Exception as e:
         raise RuntimeError("Error Running inference with local model", e)
@@ -320,8 +320,8 @@ df_init = pd.DataFrame(columns=['Start', 'End', 'Speaker', 'Text'])
 memory = psutil.virtual_memory()
 selected_source_lang = gr.Dropdown(choices=source_language_list, type="value", value="en", label="Spoken language in video", interactive=True)
 selected_whisper_model = gr.Dropdown(choices=whisper_models, type="value", value="base", label="Selected Whisper model", interactive=True)
-input_min_number_speakers = gr.Number(precision=0, value=2, label="Select assumed minimum number of speakers", interactive=True)
-input_max_number_speakers = gr.Number(precision=0, value=2, label="Select assumed maximum number of speakers", interactive=True)
+input_min_number_speakers = gr.Number(precision=0, value=2, label="Select minimum number of speakers", interactive=True)
+input_max_number_speakers = gr.Number(precision=0, value=2, label="Select maximum number of speakers", interactive=True)
 system_info = gr.Markdown(f"*Memory: {memory.total / (1024 * 1024 * 1024):.2f}GB, used: {memory.percent}%, available: {memory.available / (1024 * 1024 * 1024):.2f}GB*")
 download_transcript = gr.File(label="Download transcript")
 transcription_df = gr.DataFrame(value=df_init,label="Transcription dataframe", row_count=(0, "dynamic"), max_rows = 10, wrap=True, overflow_row_behaviour='paginate')