01-vyom Goto Github PK

Hi, I'm Vyom, an enthusiast for automation at scale. My research interests lie at the intersection of speech processing, machine learning, and transformers. Beside's that I'm an avid reader and enjoy playing soccer.

Current Status Quo

• 🎓  I completed my master of science in computer science at University of Florida from the CISE Department in May 2023. I completed my bachelors of technology in computer engineering from Dharmsinh Desai University in May 2021.
• 💼  I'm currently an applied scientist at Chronograph, and a research assistant at Data Science Research Lab. Previously, I interned at Apple on the Siri Text-to-Speech team as a machine learning researcher and at Amazon on the Alexa Smart Home team as an applied scientist. Before that, I worked at ISRO as a Research Intern working on the oceanographical satellite data interpretation using machine learning.
• 🔭  I’m currently working on transformers for different NLP tasks; particularly prompting large language models, automatic speech recognition for low-resource languages/multi-lingual setting, dialogue systems, speech enhancement, text-to-speech generation, and natural language generation.
• 🌱  I'm currently learning applications of deep learning, writing research papers, and improving my coding skills.
• 💬 Ask me about anything, I am happy to help. I am very much open to new research ideas and collaborations.
• 😄  Pronouns: he/him/his

^{Stats generated from README Stats.}

Breakdown of my contributions:

• Huggingface Transformers - Pull Requests.

  • Worked on adding ground-up implementation of Spec-Augment, bug fixes, and documentation fixes.

• PyTorch Ignite - Pull Requests, Issues.

  • Worked on documentation, loss function implementation, and bug fixes.

• Scikit-learn - Pull Requests, Issues.

  • Worked on documentation, and bug fixes for KDTree, BallTree algorithms.

• Julia - Pull Requests, Issues.

  • Worked on documentation.

• Keras - Pull Requests, Issues.

  • Documentation fixes.

• TensorFlow - Issues.

  • Issue for adding tunable parameters.

• Pandas - Pull Requests.

  • Worked on styling documentation, documentation fixes, and deprecation handling.

• Optuna - Pull Requests, Issues.

  • Worked on new visualization algorithm implementations, bug fixing, documentation fixes, and testing.

• Python Typeshed - Pull Requests.

  • Worked on adding type hints, bug fixes, and documentation fixes.