Kaldi-compatible feature extraction with PyTorch, supporting CUDA, batch processing, chunk proces...

Fast inference engine for Transformer models

中文 NLP 预处理、解析工具包，准确、高效、易用 A Chinese NLP Preprocessing & Parsing Package www.jionlp.com

Attempt at tracking states of the arts and recent results (bibliography) on speech recognition.

Zero-shot multimodal punctuation insertion and truecasing using Whisper

SpeechIO Leaderboard: a large, robust, comprehensive, benchmarking platform for Automatic Speech ...

Unofficial reimplementation of ECAPA-TDNN for speaker recognition (EER=0.86 for Vox1_O when train...

Efficient Training of Audio Transformers with Patchout

Code for paper in "ECAPA-TDNN Based Depression Detection from Clinical Speech"