TUSHAR VERMA
Applied Researcher at eBay.
Building and deploying image, text, and multimodal models.
I work with image models, BERT-style text models, and vLLM deployments for text and multimodal LLMs. Previously at Convin, I trained and deployed automatic speech recognition systems.
01 / RESEARCH & PAPER(S?)
MULTILINGUAL ASR
A speech recognition system for low-resource, noisy, code-mixed Indian languages. The approach fine-tunes pretrained models with text transliterated to Devanagari and groups similar-sounding characters.
02 / WRITING
RECENT ARTICLES
03 / NOTES
WORKING NOTES
Short notes on machine learning, deep learning, PyTorch, Triton, vLLM, and experiments will live here.