jm12138's repositories
CannyDetector
A python implementation of Canny Detector using numpy / scipy / torch / paddle package.
iFLYTEK-MSC-Python-SDK
一个讯飞智能语音平台 MSC 的第三方 Python SDK,支持语音唤醒、语音识别、语音合成、语音评测等功能。A third-party Python SDK for a iFLYTEK MSC. Using for ASR, TSS, KWS.
SoccerNet_Tracking_PaddleDetection
A Baseline for Multi Objective Tracking (MOT) of Soccer and Soccer Players Based on SoccerNet Tracking Dataset and PaddleDetection.
WenxinWorkshop-Python-SDK
一个文心千帆平台的第三方 Python SDK。A third-party Python SDK for a WenxinWorkshop.
AudioLDM
AudioLDM: Generate speech, sound effects, music and beyond, with text.
bark
🔊 Text-Prompted Generative Audio Model
ChatRWKV
ChatRWKV is like ChatGPT but powered by RWKV (100% RNN) language model, and open source.
DiffSinger
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Forked and maintained by the OpenVPI community
FastDeploy
⚡️An Easy-to-use and Fast Deep Learning Model Deployment Toolkit
gigagan-pytorch
Implementation of GigaGAN, new SOTA GAN out of Adobe
litellm
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
llama-cpp-python
Python bindings for llama.cpp
MiDaS
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
paddlecrepe
Pytorch implementation of the CREPE pitch tracker
PaddleDetection
Object detection and instance segmentation toolkit based on PaddlePaddle.
PaddleHub
Awesome pre-trained models toolkit based on PaddlePaddle.(300+ models including Image, Text, Audio and Video with Easy Inference & Serving deployment)
PaddleTest
PaddlePaddle TestSuite
RWKV-LM
RWKV is a RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.
SoccerNet_ReID_PaddleClas
A Baseline for Re-IDentification (ReID) of Soccer Players Based on SoccerNet ReID Dataset and PaddleClas.
teco-pytorch-image-models
The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more
teco-ultralytics
NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite
TTNet-Real-time-Analysis-System-for-Table-Tennis-Pytorch
Unofficial implementation of "TTNet: Real-time temporal and spatial video analysis of table tennis" (CVPR 2020)
ZoeDepth
Metric depth estimation from a single image