Sumedh Khodke

Logo

Projects

  1. Custom Named-Entity-Recognition using BERT Technologies: Python, PyTorch, FastAPI
    View Project Designed and developed a Custom NER model using transfer learning on BERT, acting as a resume parser to extract useful information from resumes based on user-defined fields such as Education, Skills, Experience, Location, Interests, etc. The model achieved an accuracy of 74% and was served as an application wrapped using FastAPI.

  2. Automatic Speech Recognition using Wav2Vec2 XLSR-53 for Low-Resource Languages Technologies: Python, PyTorch, HuggingFace
    View Project Trained the language model of facebook/wav2vec2-large-xlsr-53 on Marathi language for ASR by fine-tuning on the Open SLR64 Marathi dataset. Achieved a Word Error Rate (WER) on the test set of 12.70% with input data sampled at 16kHz. Implemented as part of the HuggingFace XLSR Open-Source Sprint for low-resource languages.

  3. NFL RosterGen: Optimizing NFL Roster Construction using Genetic Algorithms View Project Roster construction and optimization in the NFL to create better team construction strategies using a family of genetic algorithms to objectively select players, coupled with an ML-based fitness function used to evaluate a team’s quality.

  4. NLP Playground Technologies: Python, PyTorch-Lightning, FastAPI, AWS Lambda
    View Project Trained and fine-tuned different domain-specific language models of BERT variants for downstream NLP tasks like masked and unmasked text prediction and abstractive text summarization. The solution was deployed on a serverless cloud.

  5. Prediction and Semantic Classification of Myers-Briggs Personality Types from User-Provided Text Technologies: Python, PyTorch
    View Project Sponsored final year undergrad research project. Architected a model that predicts personality type according to MBTI based on user-written text input, with a comparative study of classification techniques for word-vector representations and embeddings. Achieved an accuracy score of 78% on predicted personality types.

  6. Abstractive Text Summarization using Transformers Technologies: Python, PyTorch
    View Project Performed extractive text summarization on Amazon product reviews across multiple categories. Improved the generalization of model performances of BART, T5, and PEGASUS to adapt to out-of-domain text inputs through fine-tuning.