ruohoruotsi

llama.cpp

LLM inference in C/C++

python-fire

Python Fire is a library for automatically generating command line interfaces (CLIs) from absolutely any Python object.

instruct-pix2pix

stable-diffusion-videos

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

sd-webui-deforum

Deforum extension for AUTOMATIC1111's Stable Diffusion webui

asteroid

The PyTorch-based audio source separation toolkit for researchers

audio-ai-timeline

A timeline of the latest AI models for audio generation, starting in 2023!

OpenAudio

A list of open source VST/audio plugin projects. Please contribute more links or open source your own plugins.

omnizart

Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.

Practical-RIFE

We are developing more practical approach for users based on RIFE.

pysepm

Python implementation of performance metrics in Loizou's Speech Enhancement book

SRMRpy

Python implementation of the SRMR toolbox

Quality-Net

Quality-Net: An End-to-End Non-intrusive Speech Quality Assessment Model based on BLSTM. (Interspeech, 2018, with Travel Grants)

ppg_vc

Implementation of voice conversion system utilizing phonetic posteriorgrams (status: archive)

PidginUNMT

Unsupervised Neural Machine Translation from West African Pidgin (Creole) to English without a single parallel sentence

Intelligibility-MetricGAN

Implementation for paper "iMetricGAN: Intelligibility Enhancement for Speech-in-Noise using Generative Adversarial Network-based Metric Learning"

MOSA-Net-Cross-Domain

pySIIB

A python implementation of Speech intelligibility in bits (SIIB)

iwslt-autodub-task

sti-wav

Speech Transmission Index (STI) from real speech waveforms

stoi-vqcpc

Repository for paper "Non-intrusive speech intelligibility prediction from discrete latent representations"

py-intelligibility

Python implementation of a few speech intelligibility prediction algorithms

spotpl

A CLI utility that matches files from your local music library to a Spotify playlist

speech-intelligibility-meter

MTI-Net

THDSI

Total Harmonic Distortion for Speech Intelligibility

audioObfuscation

A python function to extract the LPC coefficients of recorded speech and replace them with obfuscating coefficients. Based on this paper: https://www.fxpal.com/publications/audio-privacy-reducing-speech-intelligibility-while-preserving-environmental-sounds.pdf

speech_intelligibility_estimation

DTW_Phoneme

Computes the Dynamic Time Warping between two phoneme sequences.

prores-proxy-generator

Create ProRes Proxies using FFMPEG