nlp

Data preparation utility for the finetuning of OpenAI's Whisper model.

Generate multi-speaker conversational datasets for LLM fine-tuning. N-persona support, topic variation, conversation continuation, creative briefs with web search, character pools, Docker support. ShareGPT format with configurable role mapping.

ESGenius: EMNLP 2025 Main Oral benchmark for LLM ESG and sustainability knowledge, with 1,136 questions, evaluation code, interactive heatmap, and Hugging Face dataset release.

Production-ready Retrieval Augmented Generation (RAG) system with hybrid retrieval, advanced evaluation metrics, and monitoring. Build enterprise LLM applications with reduced hallucinations, better context management, and comprehensive observability.

Embeddable vector database for Rust and Python. HNSW indexing, metadata filtering, hybrid search, and snapshots. The SQLite of vector search.

A research-oriented training and evaluation framework for ECG-Language Models (ELMs)

Ensemble PhoBERT with FastText Embedding to improve performance on Vietnamese Sentiment Analysis tasks.

BERT finetuned on NER downstream tasks

Pizzly, financial market analysis combining technical indicators with LLMs, featuring real-time data processing and AI-powered market insights ⚡️

Re-ranking task using MS MARCO dataset and Hugging Face library

Genie in the Box: Distill Whisper STT => Mistral-7B => Phind/Phind-CodeLlama-34B-v2 => GPT 3.5 => Coqui's TTS/OpenAI TTS

AI text humanization tool with detection capabilities. Transform AI-generated content into natural, human-like writing using advanced NLP models (T5, BART, Pegasus). Features real-time AI detection, multi-model paraphrasing, and a modern Svelte frontend.

Text to emoji translation via DeepDreaming

Characterize Anything: A Wondrous Chemical Reaction between vision models and AI Characters

Recurrence Meets Transformers for Universal Multimodal Retrieval

Fine-tuning BERT and Transformer models for NLP tasks, hands-on notebooks · HuggingFace · PyTorch

A fine tuned IndoBERT model for University Sentiment On Social Media

NLP model that determines whether a plot is anime enough

I have fineTuned FinBert Model on 4.9k Financial News Headlines, Got 81-82% ACC and it perfrom well in Financial Stock News Sentiment Analysis

An optimized FastAPI server for OpenAI's Whisper whisper-large-v3-turbo model using MLX optimization