Third-party audio effects plugins as differentiable layers within deep neural networks.

Minimalistic MP3 decoder single header library

Python audio and music signal processing library

DropClass and DropAdapt - repository for the paper submitted to Speaker Odyssey 2020

Speech synthesis, voice conversion, self-supervised learning, music generation,Automatic Speech Recognition, Speaker Verification, Speech Synthesis, Language Modeling

Master the command line, in one page

Fastest & best convert qmc 2 mp3 | flac tools

Speaker diarization based on Kaldi x-vectors using pretrained model from http://kaldi-asr.org/models/0003_sre16_v2_1a.tar.gz

Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!

Implementation of triplet loss in TensorFlow

Tensorflow implementation of "A Structured Self-Attentive Sentence Embedding"

Neural speaker recognition/verification system based on Kaldi and Tensorflow

FastCGI support for Kaldi ASR

Reference implementations of popular deep learning models.

This is a list of features, scripts, blogs and resources for better using Kaldi ( http://kaldi-asr.org/ )

A curated list of awesome Speaker Diarization papers, libraries, datasets, and other resources.

Tensorflow implementation of generalized end-to-end loss for speaker verification

Voice activity detection (VAD) toolkit including DNN, bDNN, LSTM and ACAM based VAD. We also provide our directly recorded dataset.

Moby Project - a collaborative project for the container ecosystem to assemble container-based systems

PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.

End-to-end Automatic Speech Recognition for Madarian and English in Tensorflow

A deep neural network for finding text-independent speaker embedding written in tensorflow

A Deep Learning based project for colorizing and restoring old images

Neural network 3D visualization framework, build interactive and intuitive model in browsers, support pre-trained deep learning models from TensorFlow, Keras, TensorFlow.js

An AI for Music Generation

This repo implements PyramidBox with pytorch

Singing Voice Separation via Recurrent Inference and Skip-Filtering Connections - PyTorch Implementation. Demo:

Scalable, Available, Stable, Performant, and Intelligent System Design Patterns