Update app.py

app.py

@@ -359,14 +359,39 @@ with block:
 
     with gr.Accordion("What is YouTube Insights?", open=False):
         gr.Markdown(
-            "YouTube Insights is a tool developed with academic purposes only, that creates summaries, keywords and sentiments analysis based on YouTube videos or user audio files."
+            "YouTube Insights is a tool developed for academic purposes that allows you to analyze YouTube videos or audio files. It provides features like transcription, summarization, keyword extraction, sentiment analysis, and word cloud generation for multimedia content."
         )
 
-    with gr.Accordion("How does it work?", open=False):
+    with gr.Accordion("How does YouTube Insights work?", open=False):
         gr.Markdown(
-            "Works by using OpenAI's Whisper, BART for summarization and VoiceLabT5 for Keyword Extraction."
+            "YouTube Insights leverages several powerful AI models and libraries. It uses OpenAI's Whisper for Automatic Speech Recognition (ASR) to transcribe audio content. It summarizes the transcribed text using Facebook's BART model, extracts keywords with VoiceLabT5, performs sentiment analysis with DistilBERT, and generates word clouds."
         )
 
+    with gr.Accordion("What languages are supported for the analysis?", open=False):
+        gr.Markdown(
+            "YouTube Insights supports multiple languages for transcription and analysis. You can select your preferred language from the available options when using the app."
+        )
+
+    with gr.Accordion("Can I analyze audio files instead of YouTube videos?", open=False):
+        gr.Markdown(
+            "Yes, you can analyze audio files directly. Simply upload your audio file to the app, and it will provide the same transcription, summarization, keyword extraction, sentiment analysis, and word cloud generation features."
+        )
+
+    with gr.Accordion("What are the different model sizes available for transcription?", open=False):
+        gr.Markdown(
+            "The app uses a Speech-to-text model that has different training sizes, from tiny to large. Hence, the bigger the model the accurate the transcription."
+        )
+
+    with gr.Accordion("How long does it take to analyze a video or audio file?", open=False):
+        gr.Markdown(
+            "The time taken for analysis may vary based on the duration of the video or audio file and the selected model size. Shorter content will be processed more quickly."
+        )
+    
+    with gr.Accordion("Who developed YouTube Insights?" ,open=False):
+        gr.Markdown(
+            "YouTube Insights was developed by students as part of the 2022/23 Master's in Big Data & Data Science program at Universidad Complutense de Madrid for academic purposes (Trabajo de Fin de Master)."
+        )
+    
     gr.HTML(
         """
         <div style="text-align: center; max-width: 500px; margin: 0 auto;">