Awesome speech/audio LLMs, representation learning, and codec models

This is the repo of the manuscript "Embedding and Beamforming: All-Neural Causal Beamformer for Multichannel Speech Enhancement", which was submitted to ICASSP2022.

Code for the ICASSP-2021 paper: Continuous Speech Separation with Conformer.

An open source dataset for source separation

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

An open source dataset for source separation

End-to-End Speech Processing Toolkit

A PyTorch implementation of End-to-End Neural Diarization

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

Run TensorFlow on ESP32 chips without pain

PyTorch implementation of YOLO-v1 including training

Conformer: Convolution-augmented Transformer for Speech Recognition

End-to-End Neural Diarization

Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).