Different implementations of "Weighted Prediction Error" for speech dereverberation

Feedback-driven Update & Enrichment through Lookup for LLM Agent Tool Discovery

A python package to build AI-powered real-time audio applications

Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL

A collection of MCP clients.

Accessible large language models via k-bit quantization for PyTorch.

Measuring Biases in Masked Language Models for PyTorch Transformers. Support for multiple social biases and evaluation measures.

ACL 2022: An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models.

Project to reimplement and extend the baseline results found in the paper: Deep Double Descent: Where Bigger Models and More Data Hurt (https://arxiv.org/pdf/1611.03530.pdf)

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

A repository for code used to produce the results the ICASSP 2024 paper: "SELF-SUPERVISED PRETRAINING FOR ROBUST PERSONALIZED VOICE ACTIVITY DETECTION IN ADVERSE CONDITIONS"

An unofficial implementation of the Personal VAD speaker-conditioned voice activity detection method. Bachelor's thesis project.

🔊 Create labeled datasets, enhance audio quality, identify speakers, support diverse dataset types. 🎧👥📊 Advanced audio processing.

Stable Diffusion with Core ML on Apple Silicon

Source code for the X Recommendation Algorithm

Advanced Architecture Labs with CVA6

Collection of Summer 2026 tech internships!