Lists (1)
Stars
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
Python packaging and dependency management made easy
Easily train a good VC model with voice data <= 10 mins!
A book-in-progress about the Linux kernel and its insides.
Code and documentation to train Stanford's Alpaca models, and generate the data.
OCR, layout analysis, reading order, table recognition in 90+ languages
An extremely fast Python type checker and language server, written in Rust.
Modular visual interface for GDB in Python
An open access book on scientific visualization using python and matplotlib
🚴 Call stack profiler for Python. Shows you why your code is slow!
Noise supression using deep filtering
Schedule-Free Optimization in PyTorch
YaRN: Efficient Context Window Extension of Large Language Models
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
Repository for training models for music source separation.
DiffWave is a fast, high-quality neural vocoder and waveform synthesizer.
Innovation-first digital audio workstation (DAW), instrument and effect plugins, wave editor
[ICML'24 Spotlight] LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuning
Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196
A small utility making use of the pypdf library to provide a (somewhat) lighter alternative to pdftk
Speaker embedding (d-vector) trained with GE2E loss