a-n-rose
Follow
Stars
The open source Firebase alternative. Supabase gives you a dedicated Postgres database to build your web, mobile, and AI applications.
Browser based Interface for Generative AI. Chat/Agent/Taskmanager Hybrid.
A WebAssembly implementation of the C Fast Fourier Transform library kissFFT
WebAssembly build of a small, pretty fast FFT library (PFFFT).
Lightweight WASM Postgres with real-time, reactive bindings.
A fasttrack implementation in python
Kaldi recipes for the UltraSuite repository
Tools to process the UltraSuite data
Speech Processing Toolbox for MATLAB
C++ and MATLAB code for fast and accurate fundamental frequency estimation
Pitch detection and pitch tracking, voicing unvoicing detection (VAD)，基音检测
Interspeech repository
Package containing the tools necessary for decomposing a speech signal into its modulated components (also known as AM-FM decomposition). Includes the algorithms of the QHM family and the YAAPT pit…
Dr.VOT is an a software package for automatic measurement of voice onset time (VOT).
Trainable algorithm for automatic measurement of voice onset time
VOT-CP (VOT coding and predictions) is a Python program that allows for the automatic codification of phonetically aligned data in order to obtain voice onset time (VOT) predictions.
Effortlessly extract information from unstructured data with this library, utilizing advanced AI techniques. Compose AI in customizable pipelines and diverse sources for your projects.
FeedForward Propagation Through Time on Spiking Neural Network (SNNs)
Improved speech enhancement with the Wave-U-Net, a deep convolutional neural network architecture for audio source separation, implemented for the task of speech enhancement in the time-domain.
A deep learning model for classifying audio frames into [SPEECH, KCHI, CHI, MAL, FEM] classes.
Automatic LInguistic Unit Count Estimator (ALICE)
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
Simple text to phones converter for multiple languages
A collection of pre-trained, state-of-the-art models in the ONNX format