A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

The official pytorch implemention of the Intespeech 2024 paper "Reshape Dimensions Network for Speaker Recognition"

Avoids race condition when acquiring GPUs in exclusive mode

A Corpus for Research on Robust Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications

A playbook for systematically maximizing the performance of deep learning models.

kiwano

Foundational model for human-like, expressive TTS

Linux GUI application for blazingly fast and simple power-management.

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

Speech, Language, Audio, Music Processing with Large Language Model

Re-implementation of SLAM-ASR paper's experiment, using Phi-2 and Hubert

SLT 2024 Challenge: Post-ASR-Speaker-Tagging

Python wrappers for Kaldi Levenshtein's distance and alignment code.

Data and code for grapheme-to-phoneme transducers in lots of languages

Author's code of "Speaker anonymization using neural audio codec language models" (ICASSP 2024).

Download Komoot tracks and highlights as GPX files (including metadata). Supports bulk-download

Display bitahub GPU status in tmux status line.

🖼 imgcat in Python (for iTerm2)

TorchCFM: a Conditional Flow Matching library

The missing reverse proxy for ssh scp

Notify on new X clipboard events

Control for routing in Leaflet

This Dockerfile packages SOGo compiled from the sources from Alinto/sogo together with NGINX and memcached.

The SINr approach to train interpretable word and graph embeddings

Discriminative Condition-Aware PLDA

Fast PyTorch based DSP for audio and 1D signals

Pitch-shifting, time-stretching, and vocoding of speech with Controllable LPCNet (CLPCNet)

Production First and Production Ready End-to-End Keyword Spotting Toolkit

graftr: an interactive shell to view and edit PyTorch checkpoints.