Carl Thomé's Projects
a GitHub action to run `pre-commit`
(ML) audio engineering i/o utils
Community list of startups working with AI in audio and music technology
Official Repo for Google Cloud AI Platform
Representation Learning for the Automatic Indexing of Sound Effects Libraries (ISMIR 2022): Deep audio embeddings pre-trained on UCS & Non-UCS-compliant datasets.
lyrics-to-audio-alignement system. Decoding with Viterbi forced alignment. Note duration aware decoding
Easily create a simple and maintainable website for showcasing audio examples
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.
Text-to-Audio/Music Generation
cross-library (GStreamer + Core Audio + MAD + FFmpeg) audio decoding for Python
Scrape audio from YouTube and SoundCloud with a simple command-line interface.
Object-oriented handling of audio data, with GPU-powered augmentations, and more.
Playing around with automatic differentiation implementations for my own learning
Apache Beam is a unified programming model for Batch and Streaming data processing.
Codes for ISMIR 2022 paper: Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-Attention
BeatNet is state-of-the-art (Real-Time) and Offline joint music beat, downbeat, tempo, and meter tracking system using CRNN and particle filtering. (ISMIR 2021's paper implementation).
:green_book: This repo generates my personal blog
Batch normalized LSTM for tensorflow
My personal website.
Cerulean Crayons website
Audio Plugin API
Just testing Cloud Code's template
Samples for Google Cloud Machine Learning Engine
My solutions to various competitive programming problems.
Cukiverb is a real-time convolution reberb for the Digital Audio Workstation (DAW) Reaper. This work represents the outcome of my undergraduate studies Final Project.
CVXOPT -- Python Software for Convex Optimization
🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools