Starred repositories
Android style RecyclerView implemented in C++ as a Qt widget
High-quality multi-lingual text-to-speech library by MyShell.ai. Support English, Spanish, French, Chinese, Japanese and Korean.
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，Qwen2.5等模型应用在纠错场景，开箱即用。
Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
Script to build offline deb software sources
Silero VAD: pre-trained enterprise-grade Voice Activity Detector
Image restoration with neural networks but without learning.
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
A tensorflow implementation of Arxiv Paper "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose "(https://arxiv.org/abs/1811.12004)
🤖 💬 Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Turn a MacBook into a Touchscreen with $1 of Hardware
A New Loss Function for CNN Classifier Based on Pre-defined Evenly-Distributed Class Centroids
Keras implementation of ArcFace, CosFace, and SphereFace
Keras implementation of various loss functions in face recognition and visualization on Mnist
TensorFlow wheels built for latest CUDA/CuDNN and enabled performance flags: SSE, AVX, FMA; XLA
Tool for easily loading pre-trained ImageNet models into TensorFlow
Large-Margin Softmax Loss, Angular Softmax Loss, Additive Margin Softmax, ArcFaceLoss And FocalLoss In Tensorflow
The convertor/conversion of deep learning models for different deep learning frameworks/softwares.
Center Loss implementation with TensorFlow
Repo for counting stars and contributing. Press F to pay respect to glorious developers.
State-of-the-art 2D and 3D Face Analysis Project
AWTK = Toolkit AnyWhere(a cross-platform embedded GUI)
Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow