Pinned Repositories
athena-signal
awesome-ml-model-compression
Awesome machine learning model compression research papers, tools, and learning material.
DeepComplexCRN
fmt
A modern formatting library
lectures
Material for cuda-mode lectures
Linux-Kernel-Programming_2E
Linux Kernel Programming 2E - published by Packt
llamafile
Distribute and run LLMs with a single file.
lottery_mir
Ultra-light MIR models with a structured lottery ticket hypothesis approach
lulu
1D LULU smoothers to deal with pulse like noises in spectra measurement.
model_optimization
Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.
victorVoice's Repositories
victorVoice/athena-signal
victorVoice/awesome-ml-model-compression
Awesome machine learning model compression research papers, tools, and learning material.
victorVoice/DeepComplexCRN
victorVoice/fmt
A modern formatting library
victorVoice/lectures
Material for cuda-mode lectures
victorVoice/Linux-Kernel-Programming_2E
Linux Kernel Programming 2E - published by Packt
victorVoice/llamafile
Distribute and run LLMs with a single file.
victorVoice/lottery_mir
Ultra-light MIR models with a structured lottery ticket hypothesis approach
victorVoice/lulu
1D LULU smoothers to deal with pulse like noises in spectra measurement.
victorVoice/model_optimization
Model Compression Toolkit (MCT) is an open source project for neural network model optimization under efficient, constrained hardware. This project provides researchers, developers, and engineers advanced quantization and compression tools for deploying state-of-the-art neural networks.
victorVoice/next-gen-kaldi-wechat
victorVoice/noisereduce
Noise reduction in python using spectral gating (speech, bioacoustics, audio, time-domain signals)
victorVoice/SDDNet
Coarse implement of the paper "A Simultaneous Denoising and Dereverberation Framework with Target Decoupling", On DNS-2020 dataset, the DNSMOS of first stage is 3.42 and second stage is 3.47.
victorVoice/Speech_Feature_Extraction
Feature extraction of speech signal is the initial stage of any speech recognition system.
victorVoice/TAPLoss
victorVoice/RealMAN
A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization
victorVoice/tflm_tinylstm
tflm instantiation for tinylstm
victorVoice/Torch-Pruning
[CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs