Hello, I am Aditya and I am currently into

Seq2Seq Models and AI Research.

I am an Intern at JoshTalks, where I am working on building Datasets for ASR Research. My work focuses on pushing the boundaries of Speech Recognition systems by fine-tuning models like OpenAI's Whisper, Meta's Wav2Vec2, Nvidia's Canary and other seq2seq models to handle the complexities of Indian languages and real-world noisy audio.

I've built a strong foundation but still I'm always learning. Based in India, I'm open to Machine Learning and Data Science roles, bringing hands-on experience and ownership.

Have a look at my resume.

Sometimes I write here.