Jinle Tong's repositories
speech-transformer-pytorch_lightning
ASR project with pytorch-lightning
speech_recognition
end2end asr system with ctc + dynamic cnn transformer, well organized using custom template
spec_augment_layer_pytorch
a spec augment layer as a module in PyTorch model
tfrecord_builder
a wrapped class for writing tfrecord and build DataLoader using tf.data with tf2.0, almost fully automaticlly
batched-beam-decoder-pytorch
a batched version for beam decode in seq2seq model
TransformersZoo
a collection of transformers in pytorch1.0
docker_image
docker images with pytorch lightning and pytorch
ImageCaptioning.pytorch
I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)
PopTransformer
PopTransformer provides a fundamental framework(including layers, operators, models, etc) that allow users to develop and run highly optimized transformer-based models(inference-only) with Poplar SDK on Graphcore IPU.
portfolio-examples
Demonstrators and experimental applications for ML using Graphcore IPUs
project_template
project template for PyTorch using PyTorch_lightning
spec_augment
🔦 A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
wenet
Production First and Production Ready End-to-End Speech Recognition Toolkit