Pinned Repositories
cnn-tf-keras-audio-classification
Feature extraction from sound signals along with complete CNN model and evaluations using tensorflow, keras and, librosa for MFCC generation
deep-person-reid
Torchreid: Deep learning person re-identification in PyTorch.
DPCSpell
A Denoising Transformer-based Detector-Purificator-Corrector Framework for Spelling Error Correction
EfficientConformer
Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition
ForwardTacotron
⏩ Generating speech in a single forward pass without any attention!
FRCRN
Fre-GAN-pytorch
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
fuzzy
Spell checking and fuzzy search suggestion written in Go
Hindi-word-prosody
ng2-nouislider
Angular2 noUiSlider directive
kafan1986's Repositories
kafan1986/DPCSpell
A Denoising Transformer-based Detector-Purificator-Corrector Framework for Spelling Error Correction
kafan1986/cnn-tf-keras-audio-classification
Feature extraction from sound signals along with complete CNN model and evaluations using tensorflow, keras and, librosa for MFCC generation
kafan1986/deep-person-reid
Torchreid: Deep learning person re-identification in PyTorch.
kafan1986/EfficientConformer
Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition
kafan1986/ForwardTacotron
⏩ Generating speech in a single forward pass without any attention!
kafan1986/FRCRN
kafan1986/Fre-GAN-pytorch
Fre-GAN: Adversarial Frequency-consistent Audio Synthesis
kafan1986/fuzzy
Spell checking and fuzzy search suggestion written in Go
kafan1986/Hindi-word-prosody
kafan1986/ng2-nouislider
Angular2 noUiSlider directive
kafan1986/opencv-android-sdk-with-contrib
opencv341 android sdk with contrib module build on windows.
kafan1986/OpenCV_with_contrib_on_Android
Android studio集成OpenCV3.4.0及其contrib
kafan1986/Peppa-Facial-Landmark-PyTorch
Facial Landmark Detection based on PyTorch
kafan1986/senic.cryptoyaml
A python library to manage encrypted YAML files
kafan1986/silero-vad
Silero VAD: pre-trained enterprise-grade Voice Activity Detector, Language Classifier and Spoken Number Detector
kafan1986/Yolo-FastestV2
:zap: Based on Yolo's low-power, ultra-lightweight universal target detection algorithm, the parameter is only 250k, and the speed of the smart phone mobile terminal can reach ~300fps+