mrfakename's repositories
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.
metavoice-src
Foundational model for human-like, expressive TTS
TransformerLens
A library for mechanistic interpretability of GPT-style language models
tts-datasets
A list of potential text-to-speech datasets
axolotl
Go ahead and axolotl questions
blog
Public repo for HF blog posts
CLAP
Learning audio concepts from natural language supervision
demucs
Code for the paper Hybrid Spectrogram and Waveform Source Separation
fakerybakery
Config files for my GitHub profile.
hljs-atom-dynamic-theme
Atom One Dark in dark mode, Atom One Light in light mode!
http-git-server
a http git server implement by flask
miniforge
A conda-forge distribution.
parsedown-extra
Markdown Extra Extension for Parsedown
pymobi
Mobipocket tools. such as unpack, remove srcs...
Rickroll-Detector
PHP Rickroll Detector
shields
Concise, consistent, and legible badges in SVG and raster format
stable-audio-tools
Generative models for conditional audio generation
TACA-TTS
Demo Page of Text-aware and Context-aware Expressive Audiobook Speech Synthesis
whisper
Robust Speech Recognition via Large-Scale Weak Supervision