Christophe Veaux's repositories
asteroid
The PyTorch-based audio source separation toolkit for researchers
boltzmann-machines
Boltzmann Machines in TensorFlow with examples
covarep
A Cooperative Voice Analysis Repository for Speech Technologies
festival
Festival Speech Synthesis System
gammatone
Gammatone-based spectrograms, using gammatone filterbanks or Fourier transform weightings.
horovod
Distributed training framework for TensorFlow.
idlak
Official home of the Idlak Speech Synthesis Toolkit
jtrans
text-to-speech alignment java software
keras
Deep Learning for humans
librosa
Python library for audio and music analysis
magphase
MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.
merlin
This is now the official location of the Merlin project.
Montreal-Forced-Aligner
Command line utility for forced alignment using Kaldi
nsgt
Non Stationary Gabor Transform (NSGT), Python implementation
open-speech-corpora
đź’Ž A list of accessible speech corpora for ASR, TTS, and other Speech Technologies
PolyglotDB
Language data store and linguistic query API
py-webrtcvad
Python interface to the WebRTC Voice Activity Detector
pyfestival
Amlapiwr Python C ar gyfer hwyluso rhaglennu gyda Festival | A Python C wrapper for simple coding with Festival
pyloudness
How loud is that file?
pysox
Python wrapper around sox.
pysptk
A python wrapper for Speech Signal Processing Toolkit (SPTK).
python-soxr
Fast and high quality sample-rate conversion library for Python
Python-Wrapper-for-World-Vocoder
A Python wrapper for the high-quality vocoder "World"
speechbrain
A PyTorch-based Speech Toolkit
spherecluster
Clustering routines for the unit sphere
SPTK
A modified version of Speech Signal Processing Toolkit (SPTK)
tensorflow-crash-course
For those who already have some basic idea about deep learning, and preferably are familiar with PyTorch.
tensorflow-gpu-install-ubuntu-16.04
Tensorflow GPU install instructions for ubuntu 16.04 - Deep learning
wavenet_vocoder
WaveNet vocoder
WaveRNN
Pytorch implementation of Deepmind's WaveRNN model