User tools for Spark RAPIDS

NeMo text processing for ASR and TTS

Heavily optimized library for DEFLATE/zlib/gzip and NVIDIA GDEFLATE compression and decompression

NVIDIA cuOpt examples for decision optimization

An Adaptive Pencil Decomposition Library for NVIDIA GPUs

Provides training, inference and voice conversion recipes for RADTTS and RADTTS++: Flow-based TTS models with Robust Alignment Learning, Diverse Synthesis, and Generative Modeling and Fine-Grained Control over of Low Dimensional (F0 and Energy) Speech Attributes.