About

Top 1% CS student at Sharif University with a Mechanical Engineering minor. Head TA for Python, TA for Discrete Math and Numerical Computations. Experienced in Python, Java, and MATLAB. Researching robust speech recognition for diverse voices and distributed computing. Founder of IMECO, an international initiative for math education.
My Research Interests

I'm interested in a wide range of topics in computer science. Specifically here are a few of my favorites. Feel free to DM me for a collaboration.

Computer Vision and Image Processing
Deep Learning and Contrastive Learning
Software Engineering
Human-Computer Interaction
Applied Machine Learning and Optimization

Academic Experience

My Projects

Check out my latest work

I've worked on a variety of projects. Here are a few of my favorites. Feel free to check my GitHub for more.

B.Sc. Thesis

B.Sc. Thesis

Engineered a dynamic lexicon-grounded LLM correction framework to mitigate high word error rates in Persian child speech recognition across Whisper, Vosk, Qwen, and multimodal LLMs.
Python
LLM
Whisper
Text Normalization

Digital Image Processing

Implemented object detection and image restoration techniques, including Normalized Cross-Correlation, PatchMatch-based texture synthesis, and inpainting for missing regions.
Python
OpenCV

Blueprint Hell

A Java-based educational puzzle game simulating network packet routing. Built using SOLID principles, design patterns (Factory, Observer, Strategy, State), Hibernate ORM, client-server networking, and MVC architecture.
Java
Hibernate ORM
Client-Server Networking

Spotify Beats

A web-based music player that dynamically displays the currently playing song or episode from your Spotify account. It fetches real-time data from Spotify's API and shows details like the song title, artist, and album art.
HTML
CSS
JavaScript
API
Cloudflare Workers
Publications

I enjoy contributing to knowledge

Throughout my academic journey, I have authored/co-authored 2+ papers and articles. These publications span various topics, reflecting my deep interest in advancing research and solving complex problems. It has been incredibly rewarding to share my findings and contribute to the broader scientific community.

  • E

    Enhancing Automatic Speech Recognition for Child Speech in Low-Resource Languages

    Amin Hashemi

    B.Sc. Thesis. Improved ASR robustness for child speech by developing a dynamic, lexicon-grounded LLM correction framework. The system reduces word and character error rates for Whisper, Vosk, Qwen, and multimodal LLMs in low-resource Persian speech datasets.
  • S

    Survey on Reliability, Fault Tolerance, and Resilience in Distributed Systems

    Arash Vaezi, Amin Hashemi, et al.

    Lead student co-author synthesizing insights from 100+ papers, analyzing over 30 reliability and resilience challenges, and outlining 24 open problems, 16 future directions, and 23 mitigation strategies (Manuscript in preparation).

Skills

Python
Java
C
SQL
MIPS32 Assembly
TensorFlow
PyTorch
scikit-learn
Keras
OpenCV
Pandas
NumPy
Matplotlib
MATLAB
R
HTML
CSS
JavaScript
Next.js
Cloudflare Workers
SolidWorks
Rhinoceros
MaxSurf
Git
Docker
InfluxDB
LaTeX
Figma
Scrum
Contact

Get in Touch

Want to chat? Just shoot me a dm with a direct question on email and I'll respond whenever I can. I will ignore all soliciting.