wav2vec2-base-960h

Meta-Lingo is a comprehensive desktop application designed for corpus linguistics research. Built with modern technologies (Electron + React + Python FastAPI), it provides powerful tools for multimodal corpus management, linguistic analysis, and annotation.

Multi-Teacher Knowledge Distillation for Accented English Speech Recognition

ASR with Facebook's Wav2Vec2 model for accurate 🎙️ to 📝 conversion.

Engineered an ensemble AI model to detect AI-generated audio using DNN, CNN, and Wav2Vec2.0, deployed via an interactive Streamlit app.

A minimalistic automatic speech recognition streamlit based webapp powered by wav2vec2-base-960h Facebook model provided by HuggingFace transformers and the NL API provided by expert.ai

Codebase and scripts from our IEEE ICCIT 2023 paper.

AI-based system for speech emotion detection and speaker identification using ML models (SVM, MLP, XGBoost)

Fine tuned facebook/Wav2Vec2-960h-base for the purpose of speech based task detection relevant to banking and finances, of an individual.