VictorBeraldo

build-your-own-x

Master programming by recreating your favorite technologies from scratch.

Real-Time-Voice-Cloning

Clone a voice in 5 seconds to generate arbitrary speech in real-time

crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

pyannote-audio

Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding

machine-learning

:earth_americas: machine learning tutorials (mainly in Python3)

Resemblyzer

A python package to analyze and compare voices with deep learning

audio

Data manipulation and transformation for audio signal processing, powered by PyTorch

s3prl

Self-Supervised Speech Pre-training and Representation Learning Toolkit

repo2docker

Turn repositories into Jupyter-enabled Docker images

awesome-python-scientific-audio

Curated list of python software and packages related to scientific research in audio

jupyterlab-vim

:neckbeard: Vim notebook cell bindings for JupyterLab

torch-audiomentations

Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.

PyTorch_Speaker_Verification

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

VGG-Speaker-Recognition

Utterance-level Aggregation For Speaker Recognition In The Wild

pytorch_xvectors

Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196

wav2vec2-sprint

You-Only-Speak-Once

Deep Learning - one shot learning for speaker recognition using Filter Banks

NeuralPlda

Implementation of Neural PLDA (NPLDA) model (A discriminative backend for Speaker Verification)

SpeakerEmbeddingLossComparison

Companion repository for the paper "A Comparison of Metric Learning Loss Functions for End-to-End Speaker Verification" published at SLSP 2020

AM-SincNet

The Additive Margin SincNet (AM-SincNet) is a new approach for speaker recognition problems which is based in the neural network architecture SincNet and the additive margin softmax (AM-Softmax) loss function. It uses the architecture of the SincNet, but with an improved AM-Softmax layer.

agevoxceleb

feerci

FEERCI: A Package for Fast non-parametric confidence intervals for Equal Error Rates

banknoteBrazil

Classification of Brazilian paper money.

voice-unlocker

Detecção e identificação de usuários atravéz da fala dentro de um contexto de extração de features de sinais de áudio nos domínios do tempo, frequência e tempo-frequência.

training_data_speech2text

speech-emotion-recogntion-ser2022

Speech Emotion Recognition SE&R 2022

open-speech-analytics