Desh Raj's repositories
desh2608.github.io
Personal homepage for Desh Raj
alignment_restricted_transducer
An implementation of AR-RNNT loss as proposed in this paper: https://arxiv.org/abs/2011.03072
ai-deadlines
:alarm_clock: AI conference deadline countdowns
beamformer
Souden MVDR beamformer on GPU with CuPy
kaldialign
Python wrappers for Kaldi Levenshtein's distance and alignment code.
pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
queue-utils
Utility scripts to submit multi-GPU jobs on CLSP, COE, and MARCC
speech-datasets
Various speech datasets made available to the public
fast_rnnt
A torch implementation of a recursion which turns out to be useful for RNN-T.
gecko
Gecko - A Tool for Effective Annotation of Human Conversations
jsalt2020_simulate
Training data simulation
last
A JAX library for building lattice-based speech transducer models
pytorch-edit-distance
Levenshtein edit-distance on PyTorch and CUDA
scikit-learn
scikit-learn: machine learning in Python
speechbrain
A PyTorch-based Speech Toolkit
streaming_wer
CUDA implementation of Streaming WER metric