Feat: Add Audio Input Support

[Aditya062003]

Issue Title:

Enhancement: Add Audio Input Support for Generating Q&A

Issue Description:

Problem:

Currently, the software supports only text and PDF input for generating Q&A. However, there is a growing need to include audio input capabilities, allowing users to provide recorded lectures as input data.

Proposed Solution:

Integrate audio input functionality into the software to enable users to upload recorded lectures. The system should then process these audio files, extract relevant information, and generate Q&A accordingly.

Expected Behavior:

1. Users should be able to upload audio files in commonly used formats (e.g., MP3, WAV).
2. The software should process audio input, transcribe the content, and extract key points.
3. Generated Q&A should reflect the information presented in the audio lecture accurately.
4. Ensure compatibility and efficiency of audio processing across different platforms and environments.

Labels:

• enhancement
• feature-request

[charanbhatia]

@Aditya062003 please assign this issue to me. It's been a while now, and I can create a PR soon.

[samruddhi-Rahegaonkar]

@Aditya062003 Please Assign this issue to me currently working on it.

[Aditya062003]

Hey, I have already worked on a PR regarding this: #35. However, it was for the old UI, and I think we need to integrate this into the newer version.

[samruddhi-Rahegaonkar]

okay lets, Work on it.

[samruddhi-Rahegaonkar]

Is code of #35 merged in Repo ?

[red-panda3]

hii ,@Aditya062003
Please assign the issue to me , I am currently working on it

[IronJam11]

Please assign this issue to me, I am working on it :)

[IronJam11]

I have made a pr for the same, please check if need be, thank you.

[waqar2403]

It seems interesting Will happy to work on

[sakina1303]

please assign this issue to me, i would love to work on it.

[KeshavSingh2703]

Hi, I’m interested in contributing to this issue! I have experience with machine learning and natural language processing, and I’ve worked on integrating AI models with different input modalities. I believe I can help implement the audio input functionality by leveraging tools like OpenAI Whisper or Google Speech-to-Text for transcription, combined with existing Q&A generation logic.

[AvikRay1001]

@Aditya062003 is this pr opened or is it solved??