Dastgah Detection for Persian Music
Developing a model to classify Persian music Dastgah.
Projects
Faster R-CNN from Scratch
Developed a custom Faster R-CNN implementation for wildfire smoke detection.
MUSIC Algorithm
Implemented the MUSIC algorithm to estimate the Direction of Arrival (DOA) of sound sources
Emotionally Aware Robot Assistant
An emotionally aware robot assistant capable of receiving voice commands
Fine-Tuning Segment Anything Model (SAM)
Fine-tuned SAM on a custom dataset for detecting bodies of water.
Speech Emotion Recognition
Fine-tuned the HuBERT model on the SheMO: Persian Speech Emotion Detection Database.
Persian Speech-to-Text
Fine-tuned Whisper model for Persian language.
Voice Chatbot
Developed a Persian voice chatbot integrated with Whisper for speech recognition and ChatGPT for conversational responses.
LoRA Fine-Tuning
Fine-tuned RoBERTa using LoRA on the MultiNLI dataset.