ensky0

iCanHazShortcut

simple shortcut manager for macOS

poetry-cython-example

covost

CoVoST: A Large-Scale Multilingual Speech-To-Text Translation Corpus (CC0 Licensed)

silero-vad

Silero VAD: pre-trained enterprise-grade Voice Activity Detector

lhotse

Tools for handling speech data in machine learning projects.

sacrebleu

Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons

audiotools

Object-oriented handling of audio data, with GPU-powered augmentations, and more.

AcademiCodec

AcademiCodec: An Open Source Audio Codec Model for Academic Research

descript-audio-codec

State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

seamless_communication

Foundational Models for State-of-the-Art Speech and Text Translation

ExpressiveTacotron

This repository provides a multi-mode and multi-speaker expressive speech synthesis framework, including multi-attentive Tacotron, DurIAN, Non-attentive Tacotron, GST, VAE, GMVAE, and X-vectors for building prosody encoder.

VocGAN

VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network

SQLCipher-Password-Cracker-OpenCL

Password cracker for SQLCipher v2 using OpenCL

sqlcipher

SQLCipher is a standalone fork of SQLite that adds 256 bit AES encryption of database files and other security features.

translatotron

Non-Attentive-Tacotron

This is Pytorch Implementation of Google's Non-attentive Tacotron.

Parallel-Tacotron2

PyTorch Implementation of Google's Parallel Tacotron 2: A Non-Autoregressive Neural TTS Model with Differentiable Duration Modeling

Voice_Activity_Detector

A statistical model-based Voice Activity Detection

Voice-Activity-Detection

Efficient voice activity detection algorithms using long-term speech information in C++

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

FlexGen

Running large language models on a single GPU for throughput-oriented scenarios.

whisper.cpp

Port of OpenAI's Whisper model in C/C++

causal-transformer-decoder

SpeechT5

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing

Autoformer

About Code release for "Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting" (NeurIPS 2021), https://arxiv.org/abs/2106.13008

bigbird

Transformers for Longer Sequences

longformer

Longformer: The Long-Document Transformer

performer-pytorch

An implementation of Performer, a linear attention-based transformer, in Pytorch

hifi-gan

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

TransTacoS-RetuneGAN

A toy-like Text-to-Speech for Chinese/Mandarin synthesize, inspired by Tacotron & FastSpeech2 & RefineGAN.