Stars
A playbook for systematically maximizing the performance of deep learning models.
Robust Speech Recognition via Large-Scale Weak Supervision
FSA/FST algorithms, differentiable, with PyTorch compatibility.
[NeurIPS 2023] Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
Develop input methods for Windows easily with Python and node.js
A home for audio ML in JAX. Has common features, learnable frontends, pretrained supervised and self-supervised models.
A high performance and generic framework for distributed DNN training
Command line utility for forced alignment using Kaldi
Apache Arrow is the universal columnar format and multi-language toolbox for fast data interchange and in-memory analytics
ML Collections is a library of Python Collections designed for ML use cases.
functorch is JAX-like composable function transforms for PyTorch.
An attempt to answer the age old interview question "What happens when you type google.com into your browser and press enter?"
The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many mo…
This repository contains audio samples and supplementary materials accompanying publications by the "Speaker, Voice and Language" team at Google.
High performance model preprocessing library on PyTorch
[ICLR2022] Code for "Retriever: Learning Content-Style Representation as a Token-Level Bipartite Graph"
The fastest path to AI-powered full stack observability, even for lean teams.
**ICASSP 2022** 《Toward Degradation-Robust Voice Conversion》Using speech enhancement and end-to-end denoising training to improve degradation / adversarial robustness of VC models.
UniSpeech - Large Scale Self-Supervised Learning for Speech
An official reimplementation of the method described in the INTERSPEECH 2021 paper - Speech Resynthesis from Discrete Disentangled Self-Supervised Representations.
One stop solution for all Vulkan samples