ramos's repositories
acoustic_model
This is a sub-repository in building to create acoustic model in Mandarin speech recognition.
asv-subtools
An Open Source Tools for Speaker Recognition
ColossalAI
Making large AI models cheaper, faster and more accessible
CPC_audio
An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.
DeepLearningExamples
Deep Learning Examples
DetectoRS
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
DiverseBranchBlock
Diverse Branch Block: Building a Convolution as an Inception-like Unit
EnergonAI
Large-scale model inference.
neural_sp
End-to-end ASR/LM implementation with PyTorch
ParallelSpeaker
This is a repository which enables large scale speaker verification.
RamosNeMo
NeMo: a toolkit for conversational AI
rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
torchshard
TorchShard: Slicing a PyTorch Tensor Into Parallel Shards.
voxceleb_trainer
In defence of metric learning for speaker recognition
xlnet
XLNet: Generalized Autoregressive Pretraining for Language Understanding