Search Results for "learning vector quantization"

whisper.cpp is a lightweight, C/C++ reimplementation of OpenAI’s Whisper automatic speech recognition (ASR) model—designed for efficient, standalone transcription without external dependencies. The entire high-level implementation of the model is contained in whisper.h and whisper.cpp. The rest of the code is part of the ggml machine learning library. The command downloads the base.en model converted to custom ggml format and runs the inference on all .wav samples in the folder samples. whisper.cpp supports integer quantization of the Whisper ggml models. Quantized models require less memory and disk space and depending on the hardware can be processed more efficiently.

XNNPACK is a highly optimized, low-level neural network inference library developed by Google for accelerating deep learning workloads across a variety of hardware architectures, including ARM, x86, WebAssembly, and RISC-V. Rather than serving as a standalone ML framework, XNNPACK provides high-performance computational primitives—such as convolutions, pooling, activation functions, and arithmetic operations—that are integrated into higher-level frameworks like TensorFlow Lite, PyTorch...

SPTK is a suite of speech signal processing tools for UNIX environments, e.g., LPC analysis, PARCOR analysis, LSP analysis, PARCOR synthesis filter, LSP synthesis filter, vector quantization techniques, and other extended versions of them.

GloVe is an unsupervised learning algorithm for obtaining vector representations for words. Training is performed on aggregated global word-word co-occurrence statistics from a corpus, and the resulting representations showcase interesting linear substructures of the word vector space. The links provided contain word vectors obtained from the respective corpora.

The library enables to create perceptrons with desired number of inputs and customized train rate. It enables to train the perceptrons according to the user input. Check the Wiki page for usage examples and API

Simple but capable chat server. This project is more for research and development. A fully functional server along with its source code is provided but the aim for this project is to provide learning material such as detailed documentation, specs, diagrams and tutorials. There is client software also but it is on a separate project.

This project implements the parallelized version of the LBG vector quantization algorithm on Cell Broadband Engine.

libit provides easy to use yet efficient tools for C for signal processing, coding, or scientific code in general. It includes basic vector, matrix and function types, some common source and channel coding tools such as quantization, entropy coding, etc.

Ruby SVM is a Ruby binding to the very popular and highly useful libsvm library (released under a seperate license) This allows you to effortlessly experiment with machine learning, in particular Support Vector Machines, in Ruby. SVM's have found use in