JakeOne IM

utmos-pytorch. Unofficial fairseq-free PyTorch implementation of UTMOS (v1, 2022), matching the original system.

andrej-karpathy-skills. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

torch-l1-snr. Variations of L1 SNR Loss function for training audio source separation machine learning models

S3Tokenizer. Reverse Engineering of Supervised Semantic Speech Tokenizer (S3Tokenizer) proposed in CosyVoice

conditional-flow-matching. TorchCFM: a Conditional Flow Matching library

audioflow. Python

chatterbox. SoTA open-source TTS

ctm. Python

nnsvs. Neural network-based singing voice synthesis library for research

lora. Using Low-rank adaptation to quickly fine-tune diffusion models.

Open-Sora. Open-Sora: Democratizing Efficient Video Production for All

nanoGPT. The simplest, fastest repository for training/finetuning medium-sized GPTs.

NATSpeech. A Non-Autoregressive Text-to-Speech (NAR-TTS) framework, including official PyTorch implementation of PortaSpeech (NeurIPS 2021) and DiffSpeech (AAAI 2022)

ltu. Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

stftPitchShift. STFT based real-time pitch and timbre shifting in C++ and Python

ControlNet. Let us control diffusion models!

naturalspeech2-pytorch. Implementation of Natural Speech 2, Zero-shot Speech and Singing Synthesizer, in Pytorch

stylegan-t. [ICML'23] StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis

WaveRNN. WaveRNN Vocoder + TTS

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

ML-YouTube-Courses. 📺 Discover the latest machine learning / AI courses on YouTube.

neural-ode. Jupyter notebook with Pytorch implementation of Neural Ordinary Differential Equations

open-tts-tracker.

Awesome-Model-Quantization. A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

ssr_eval. Evaluation and Benchmarking of Speech Super-resolution Methods

nuwave2. NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates @ INTERSPEECH 2022

bark. 🔊 Text-Prompted Generative Audio Model

genmusic_demo_list. a list of demo websites for automatic music generation research

WeeklyArxivTalk. [Zoom & Facebook Live] Weekly AI Arxiv 시즌2

BigVGAN. Official PyTorch implementation of BigVGAN (ICLR 2023)

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

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

AudioLDM-training-finetuning. AudioLDM training, finetuning, evaluation and inference.

VideoCrafter. VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

dasp-pytorch. Differentiable audio signal processors in PyTorch

stable-diffusion. A latent text-to-image diffusion model

NSF-HiFiGAN. Vocoder NSF-HiFiGAN (Moved into deepaudio)

ddsp_pytorch. Implementation of Differentiable Digital Signal Processing (DDSP) in Pytorch

AudioSep. Official implementation of "Separate Anything You Describe"

Palette-Image-to-Image-Diffusion-Models. Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

julius. Fast PyTorch based DSP for audio and 1D signals

solid-markdown. Render Markdown as Solid components

voicefixer_main. General Speech Restoration

room-impulse-responses. A list of publicly available room impulse response datasets and scripts to download them.

PyTorch-tSNE. Python

gomin. GOMIN; Gaudio Open Mel-spectrogram Inversion Network

openl3. OpenL3: Open-source deep audio and image embeddings

awesome-tips.

audio-diffusion-pytorch. Audio generation using diffusion models, in PyTorch.

pymixconsole. Headless multitrack mixing console in Python

speechbrain. A PyTorch-based Speech Toolkit

denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch

One-sentence_Diffusion_summary. The repo for studying and sharing diffusion models.

CRASH. Jupyter Notebook

SiFiGAN. Official implementation of the source-filter HiFiGAN vocoder

pytorch-transformer-kor-eng. Transformer Implementation using PyTorch for Neural Machine Translation (Korean to English)

torch-nansypp. NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis

google-research. Google Research

kosp2e. Korean Speech to English Translation Corpus

C-DSVAE. Contrastively Disentangled Sequential Variational Audoencoder

diff-svc. Singing Voice Conversion via diffusion model

whisper. Robust Speech Recognition via Large-Scale Weak Supervision

audio-dataset. Audio Dataset for training CLAP and other models

sound_generation. Code and generated sounds for "Conditional Sound Generation Using Neural Discrete Time-Frequency Representation Learning", MLSP 2021

Awesome-Diffusion-Models. A collection of resources and papers on Diffusion Models

Text-to-sound-Synthesis. The source code of our paper "Diffsound: discrete diffusion model for text-to-sound generation"

ast. Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

guided-diffusion. Python

docker. Install Mattermost server via Docker

music_source_separation. Python

pedalboard. 🎛 🔊 A Python library for audio.

nnAudio. Audio processing by using pytorch 1D convolution network

ParallelWaveGAN. Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

tacotron2. Tacotron 2 - PyTorch implementation with faster-than-realtime inference

World. A high-quality speech analysis, manipulation and synthesis system

ISMIR2020_U_Nets_SVS. A PyTorch Implementation of the paper - Choi, Woosung, et al. "Investigating u-nets with various intermediate blocks for spectrogram-based singing voice separation." 21th International Society for Music Information Retrieval Conference, ISMIR. 2020.

sigsep-mus-eval. museval - source separation evaluation tools for python

attention-is-all-you-need-pytorch. A PyTorch implementation of the Transformer model in "Attention is All You Need".

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

python-audio-effects. Apply audio effects such as reverb and EQ directly to audio files or NumPy ndarrays.

stempeg. Python I/O for STEM audio files

LPCNet. Efficient neural speech synthesis

python-MCD. Python

gct535-2021. Code repository for GCT535 Sound Technology for Multimedia (Spring 2021)

JuceCompressor. A compressor audio plugin made with JUCE

AudioCompress. A dynamic range compressor/volume normalization library