This is your work, valued

Stockholm, Sweden

Carl Thomé

Elite
@carlthome

Music ML, audio data, self-supervised learning, differentiable programming

tensorflow-convlstm-cell. A ConvLSTM cell with layer normalization and peepholes for TensorFlow's RNN API.

400

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

396

audioscrape. Scrape audio from YouTube and SoundCloud with a simple command-line interface.

88

ml-vst. Create VST plugins with JUCE that run machine learning models.

28

dotfiles. My idiosyncratic config for personal computing

23

vscode-git-line-blame. Display inline information of the last commit that edited the currently selected line in the editor

21

mirpkgs. Nix packages for reproducible MIR research

16

drum-transcriber. Convert audio recordings of drums into MIDI files with Hidden Markov Models.

13

pmqd. Perceived Music Quality Dataset

12

ml-runtimes. Nix packages for interactive ML development

8

tfjs-gradcam. Grad-CAM implementation in TensorFlow JS.

4

motion-synth. Generate and visualize harmonic audio from a motion detected video stream with HTML5.

3

pyfasst. Python implementation of the Flexible Audio Source Separation Toolbox (FASST)

2

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

2

model-development-template. For developing new ML models with Jupyter Notebooks in VS Code

2

cvxopt. CVXOPT -- Python Software for Convex Optimization

2

bnlstm. Batch normalized LSTM for tensorflow

2

wedding. HTML

1

musicnn. Pronounced as "musician", musicnn is a set of pre-trained deep convolutional neural networks for music audio tagging.

1

vapeplot. matplotlib extension for vaporwave aesthetics

1

magenta. Magenta: Music and Art Generation with Machine Intelligence

1

worms-speechbank-synthesis. Use LLMs to generate more speech lines in the classic PC game Worms

1

nix-pip-flake. Testing Python inside a venv with nix flakes

1

maskininlarning. A translation of machine learning terms to Swedish

1

ipytoolbox. A collection of IPython magics and other utilities

1

fold. Deep learning with dynamic computation graphs in TensorFlow

1

librosa. Python library for audio and music analysis

1

posesynth. Playing around with ml5.js

1

timbre-transfer. Python

1

nix-jax-mnist. A toy example of training MNIST with JAX

1

leetspeaker. Make it easier being 1337 online with the leetspeaker.

1

gpustat. 📊 A simple command-line utility for querying and monitoring GPU status

1

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.

1

gradio-video-timeline-component. Custom Gradio component to visualize audio/video items on a timeline

1

gpt-engineer. Specify what you want it to build, the AI asks for clarification, and then builds it.

1

onnx-js-audio-test. Nix

1

meson-build-test. Testing Meson for fun and learnings

1

msaf-encodec. Music structure analysis with deep embeddings

1

poetry2nix-example. Playing around with poetry2nix to learn more about Nix for Python development

1

stable-audio-tools. Generative models for conditional audio generation

1

AlignmentDuration. lyrics-to-audio-alignement system. Decoding with Viterbi forced alignment. Note duration aware decoding

1

bark-example. Python

1

public_plstm. Phased LSTM

1

music-loops-with-librosa. A little Streamlit app that lets visitors create music loops with librosa and NumPy

1

golisten. An open source platform for browser based speech and audio subjective quality tests.

1