Ilaria Manco

audio-file-mcp-app. An MCP App for playing and inspecting local audio files in an MCP host.

pure-vibes. Pure Data 🤝 AI Agents

the-infinite-crate. The Infinite Crate is a DAW plugin built on JUCE, React, and the Lyria RealTime live music model

magenta-realtime. Magenta RealTime 2: An Open-Weights Live Music Model

quantum-audio. A Python package for building Quantum Representations of Digital Audio. Developed by Moth.

AudioBench. AudioBench: A Universal Benchmark for Audio Large Language Models

audio-ai-hub. The hub for audio AI research: papers, open models, benchmarks & datasets across audio LLMs, speech recognition, TTS, music & audio generation.

lovely-llama. An implementation of the Llama architecture, to instruct and delight

gpu-optimization-workshop. Slides, notes, and materials for the workshop

memorization_generalization_in_diffusion_models. Jupyter Notebook

all-in-one. All-In-One Music Structure Analyzer

fadtk. A simple library for Fréchet Audio Distance (FAD) calculation

AQUA-Tk. AQUA-Tk = Audio QUality Assessment-Toolkit. (In development)

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

Academic-project-page-template. A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

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

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

llark. Code for the paper "LLark: A Multimodal Instruction-Following Language Model for Music" by Josh Gardner, Simon Durand, Daniel Stoller, and Rachel Bittner.

research-templates. LaTeX templates I created for authoring research papers

quivr. Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: PGVector, Faiss. Any Files. Anyway you want.

audiocraft. Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

msu-benchmark. music semantic understanding evaluation benchmark

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

musiclm-pytorch. Implementation of MusicLM, Google's new SOTA model for music generation using attention networks, in Pytorch

CLAP. Contrastive Language-Audio Pretraining

music_caps_dl. Unofficial download repository for MusicCaps

tuning_playbook. A playbook for systematically maximizing the performance of deep learning models.

msd-subsets. million song dataset split for extended clean tag & artist-level stratified

ismir2022-datasets. list of MIR dataset papers presented at ISMIR 2022

music-audio-representations. Results and Models for Learning Audio Representations of Music Content

awesome-music-informatics. A curated list of awesome article, tutorial, library, webpage, etc.

DJ-Tools. DJ tools for downloading, processing, and sharing music / rekordbox data.

audio-algebra. alchemy with embeddings

VQ-Diffusion. Official implementation of VQ-Diffusion

NIME_workshop.

ai-audio-startups. Community list of startups working with AI in audio and music technology

simplified-jukemir. A minimum JukeMIR branch for feature extraction.

composer. Supercharge Your Model Training

scaper. A library for soundscape synthesis and augmentation

hear-baseline. Simple baseline model for the HEAR benchmark

hear-eval-kit. Evaluation kit for the HEAR Benchmark

hear-preprocess. Dataset preprocessing code for the HEAR 2021 NeurIPS competition

s4. Structured state space sequence models

RAVE. Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder

rse-course. Materials for The Alan Turing Institute's Research Software Engineering course

perceiver-pytorch. Implementation of Perceiver, General Perception with Iterative Attention, in Pytorch

music-cocreation-tutorial. Start-to-finish tutorial for interactive music co-creation in PyTorch and Tensorflow.js

tutorial. 2021 ISMIR tutorial - music classification

soundata. Python library for downloading, loading & working with sound datasets

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

neural-waveshaping-synthesis. efficient neural audio synthesis in the waveform domain

mathematics-of-ml-course. Jupyter Notebook

meetups. Meetups data and resources archive for the London Audio & Music AI Meetup

audiomentations. A Python library for audio data augmentation. Useful for making audio ML models work well in the real world, not just in the lab.

MelSpecVAE. Variational Autoencoder in the mel-spectrogram domain for one-shot audio synthesis

uclser20. Code for the paper "Unsupervised Contrastive Learning of Sound Event Representations", ICASSP 2021.

SciencePlots. Matplotlib styles for scientific plotting

CLMR. Official PyTorch implementation of Contrastive Learning of Musical Representations

vissl. VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

Multimodal-Transformers. List of papers and resources for multimodal transformers

audio-captioning-resources. A list of resources that can help in research for automated audio captioning

auraloss. Collection of audio-focused loss functions in PyTorch

experiment-impact-tracker. Python

music4all_contrib. Jupyter Notebook

audioset_tagging_cnn. Python

checklist. Beyond Accuracy: Behavioral Testing of NLP models with CheckList

tag-based-music-retrieval. Python

webdataset. A high-performance Python-based I/O system for large (and small) deep learning problems, with strong support for PyTorch.

torchkit. Research boilerplate for PyTorch.

listening-moods. Accompanying code for our ISMIR 2020 paper on mood estimation.

matplotlib_for_papers. Handout for the tutorial "Creating publication-quality figures with matplotlib"

mirdata. Python library for working with Music Information Retrieval datasets

ismir2020-metric-learning. ISMIR 2020 Tutorial for Metric Learning in MIR

spotify-musixmatch-data-collector. A Python module to generate large scale Music datasets using both Spotify and MusixMatch API's.

meetups. Slides and resources of the Vienna Deep Learning Meetup

nnAudio. Audio processing by using pytorch 1D convolution network

WavAugment. A library for speech data augmentation in time-domain

audio-captioning-papers. A list of papers about audio captioning

sota-music-tagging-models. Python

pytorch-metric-learning. The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

PaperNotes. Important notes on scientific papers

pytorch-playground. Base pretrained models and datasets in pytorch (MNIST, SVHN, CIFAR10, CIFAR100, STL10, AlexNet, VGG16, VGG19, ResNet, Inception, SqueezeNet)

differential-privacy-library. Diffprivlib: The IBM Differential Privacy Library

pvse. Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval (CVPR 2019)

vsepp. PyTorch Code for the paper "VSE++: Improving Visual-Semantic Embeddings with Hard Negatives"

mmvae. Multimodal Mixture-of-Experts VAE

Visual-Semantic-Embeddings-an-incomplete-list. A paper list of visual semantic embeddings and text-image retrieval.

visualbert. Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"

lxmert. PyTorch code for EMNLP 2019 paper "LXMERT: Learning Cross-Modality Encoder Representations from Transformers".

VLP. Vision-Language Pre-training for Image Captioning and Question Answering

grounded-video-description. Video Grounding and Captioning

self-critical.pytorch. Unofficial pytorch implementation for Self-critical Sequence Training for Image Captioning. and others.

NeuralBabyTalk. Pytorch code of for our CVPR 2018 paper "Neural Baby Talk"

show_attend_and_tell_pytorch. Pytorch implement Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

ImageCaptioning.pytorch. I decide to sync up this repo and self-critical.pytorch. (The old master is in old master branch for archive)

a-PyTorch-Tutorial-to-Image-Captioning. Show, Attend, and Tell | a PyTorch Tutorial to Image Captioning

visual-semantic-embedding. Implementation of the image-sentence embedding method described in "Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models"

pytorch-lightning. Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

audioset-vggish-tensorflow-to-pytorch. Script for converting the pretrained VGGish model provided with AudioSet from TensorFlow to PyTorch, along with a basic smoke test.

remixmatch. Python

releasing-research-code. Tips for releasing research code in Machine Learning (with official NeurIPS 2020 recommendations)

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

pytorch-template. PyTorch deep learning projects made easy.

bert_score. BERT score for text generation

VL-BERT. Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".

mmf. A modular framework for vision & language multimodal research from Facebook AI Research (FAIR)

pytorch-normalizing-flows. Normalizing flows in PyTorch. Current intended use is education not production.

attention-primer. A demonstration of the attention mechanism with some toy experiments and explanations.

move. PyTorch code for training and evaluating MOVE, musically-motivated version embeddings

SoundSeek. SoundSeek is a new interface to search through your sound file libraries

Interactive_Tools. Interactive Tools for Machine Learning, Deep Learning and Math

confugue. Hierarchical configuration framework for Python

ctrl. Conditional Transformer Language Model for Controllable Generation

PPLM. Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

SampleVAE. Multi-purpose tool for sound design and music production implemented in TensorFlow.