Stars
Repo for the paper: "Agree to Disagree: Diversity through Disagreement for Better Transferability"
High-level library to help with training and evaluating neural networks in PyTorch flexibly and transparently.
Speech-to-text server framework with next-gen Kaldi
Speech-to-text, text-to-speech, speaker recognition, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, Raspberry Pi, RISC-V, x86_64 …
Libraries for applying sparsification recipes to neural networks with a few lines of code, enabling faster and smaller models
Simple, Elegant, Typed Argument Parsing with argparse
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
Fast and memory-efficient exact attention
FSA/FST algorithms, differentiable, with PyTorch compatibility.
🎡 Build Python wheels for all the platforms with minimal configuration.
Text utilities, including beam search decoding, tokenizing, and more, built for use in Flashlight.
A multi-voice TTS system trained with an emphasis on quality
Quantized Neural Network PACKage - mobile-optimized implementation of quantized neural network operators
Benchmark popular audio i/o packages
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
✨ Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com
Python package for combining diarization system outputs.
Fast CUDA implementation of (differentiable) soft dynamic time warping for PyTorch
a lightweight speech processing toolkit based on Pytorch and (Py)Kaldi
An unofficial styleguide and best practices summary for PyTorch
Tools for handling speech data in machine learning projects.
Python functions for reading kaldi data formats. Useful for rapid prototyping with python.
Fixes mojibake and other glitches in Unicode text, after the fact.
🔊 A comprehensive list of open-source datasets for voice and sound computing (95+ datasets).
A library for speech data augmentation in time-domain