Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Original file line number Diff line number Diff line change
@@ -0,0 +1,72 @@
---
title: "SSoC ’25 Week 02 Update by Muhammad Haroon"
excerpt: "Setting up AudioGen locally and building a simple user interface using Streamlit for generating audio from text."
category: "DEVELOPER NEWS"
date: "2025-06-15"
slug: "2025-06-15-ssoc-25-MuhammadHaroon-week02"
author: "Muhammad Haroon"
description: "SSoC'25 Contributor working on Generative AI Instrument Sample Generation for Music Blocks"
Comment on lines +7 to +8
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please follow the new format for this. You can remove the description, it will pull automatically from the authors page, and for author use the new convention. See docs to find the new convention

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@sa-fw-an I think we can merge the PR with these format issues and once author page gets merged will create a separate PR for it, fixing all the format issues.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Y raise seperate PR's, Its just a simple fix. Its better if we push it before merging. Please change and push the code

tags: "ssoc25,sugarlabs,week02,GenAI,MusicBlocks,Music"
image: "assets/Images/GSOC.png"
---

<!-- markdownlint-disable -->

# Week 02 Progress Report by Muhammad Haroon

**Project:** [Generative AI Instrument Sample Generation for Music Blocks](https://github.com/sugarlabs/GSoC/blob/master/Ideas-2025.md#Generative-AI-Instrument-Sample-Generation-for-Music-Blocks)
**Mentors:** [Walter Bender](https://github.com/walterbender), [Sumit Srivastava](https://github.com/sum2it)
**Assisting Mentors:** [Devin Ulibarri](https://github.com/pikurasa)
**Reporting Period:** 2025-06-09 - 2025-06-15

---

## Goals for This Week

- **Goal 1:** Set up AudioGen locally.
- **Goal 2:** Create a UI using streamlit.

---

## This Week's Achievements

1. **Set up AudioGen locally**
- I was able to set up AudioGen locally for that I followed [AudioGen docs](https://github.com/facebookresearch/audiocraft/blob/main/docs/AUDIOGEN.md). I also created a virtual environment and a requirements.txt file to make the project easier to run.

2. **Create a UI using streamlit**
- I also created a UI using streamlit with the help of the [Streamlit docs](https://docs.streamlit.io/).

---

## Challenges & How I Overcame Them

- **Challenge:** The challenge I actually faced was due to limited resources. AudioCraft (which provides AudioGen) requires a GPU with at least 16 GB of memory for running inference with the medium-sized models (~1.5B parameters). For generating 5 minutes duration of audio, it took around 15-20 minutes.
- **Solution:** I ran the model and used the waiting time to complete other tasks. I plan to deploy the model on AWS, where I expect significantly better performance.

---

## Key Learnings

- Gained familiarity with **Streamlit**

---

## Next Week's Roadmap

- Generate more samples using AudioGen and save them in Google Drive.

---

## Acknowledgments

Thank you to my mentors, the Sugar Labs community, and fellow GSoC contributors for ongoing support.

---

## Connect with Me

- GitHub: [@haroon10725](https://github.com/haroon10725)
- Gmail: [[email protected]](mailto:[email protected])
- LinkedIn: [Muhammad Haroon](https://www.linkedin.com/in/muhammad-haroon-7003b923b/)

---
Comment on lines +66 to +72
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is not required as we already have an authors page for that. The data will be redundant. Please remove it

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@sa-fw-an I think we can merge the PR with these format issues and once #209 gets merged will create a separate PR for it, fixing all the format issues.

Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Its better if u push before merging, otherwise there will be an extra commit and a waste of PR, when we already know that this is not needed.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@haroon10725 I merged it. Please remove the redundant info when you have the chance.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@pikurasa Thankyou, will create a PR soon removing redundant info.