I’ve been working in data science for around a decade now, mostly in the realm of Product Analytics. My focus has been building interpretable models for actionable insights.
Recently I’ve been working on a startup investigating the use of machine learning for forecasting and early detection of crop disease.
On the side, I’ve been playing around with deep learning in the audio domain and exploring time series modeling on open source data. I’m also a big fan of birds.
Posts
-
Getting to know Graph ML
-
Gemma 4 12B and Methods of Multimodal Models
-
Vector Quantization and Continous Codes in Audio ML
-
Transformer and Diffusion models, and their role in audio generation
-
Latent Spaces and Neural Codecs in Generative Audio
-
TTS Architecture Trends
-
A Timeline of TTS models
subscribe via RSS