autopilot-rs/autopy — A simple, cross-platform GUI automation module for Python and Rust.

JupyterLite: Jupyter ❤️ WebAssembly ❤️ Python

How we made Jupyter Notebooks collaborative with Yjs

VertaAI/modeldb — Open Source ML Model Versioning, Metadata, and Experiment Management

google/compare_gan

pfnet-research/sngan_projection

Spectral Normalization for Generative Adversarial Networks, code

Progressive Growing of GANs for Improved Quality, Stability, and Variation

Spoken dialogue data collected in the WAXHOLM project, dataset, phoneset

NST Pronunciation Lexicon for Swedish

shivammehta007/Neural-HMM

Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

urvashik/knnlm

SlimIPL: Language-Model-Free Iterative Pseudo-Labeling

Joint Masked CPC and CTC Training for ASR

The Curious Case of Neural Text Degeneration

lukakerr/Pine

AI Sweden Youtube

LibriVox - An Sgéaluidhe Gaedhealach by Dúbhglas de h-Íde, scan

Eclipse Mosquitto

mSLAM: Massively multilingual joint pre-training for speech and text

Wav2Vec2 Time Stamps #15687

Distilling the Knowledge of BERT for Sequence-to-Sequence ASR

google-research/t5x

google-research/mozolm — MozoLM: A language model (LM) serving library

Any-to-One Sequence-to-Sequence Voice Conversion using Self-Supervised Discrete Speech Representations

spaces/microsoft/wavlm-speaker-verification

Multistream CNN for Robust Acoustic Modeling, code, script

W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training

VocalTractLab

chdh/klatt-syn

makcedward/nlpaug

Star Temporal Classification: Sequence Classification with Partially Labeled Data

Differentiable Allophone Graphs for Language-Universal Speech Recognition, twitter thread

BPE-Dropout: Simple and Effective Subword Regularization

Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidates

Non-Autoregressive Predictive Coding for Learning Speech Representations from Local Dependencies, code

facebookresearch/CPC_audio

FastPitchFormant: Source-Filter Based Decomposed Modeling for Speech Synthesis