Interesting links, 25/9/2021
Misc. interesting things.
Add an official audio classification example #13722
To use your own dataset, convert your data into a
csvorjsonformat with the fieldsfileandlabellike so:
worldveil/dejavu — Audio fingerprinting and recognition in Python Blog
Perlence/PyGuitarPro — Read, write and manipulate GP3, GP4 and GP5 files
microsoft/muzic — Muzic: Music Understanding and Generation with Artificial Intelligence
open-mmlab/mmaction2 — OpenMMLab’s Next Generation Video Understanding Toolbox and Benchmark
Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document
lima-vm/lima — Linux virtual machines, on macOS (aka “Linux-on-Mac”, “macOS subsystem for Linux”, “containerd for Mac”, unofficially)
openai/triton — a language and compiler for writing highly efficient custom Deep-Learning primitives
mingrammer/diagrams — Diagram as Code for prototyping cloud system architectures
babysor/MockingBird — Clone a voice in 5 seconds to generate arbitrary speech in real-time
iperov/DeepFaceLive — Real-time face swap for PC streaming or video calls
HarisIqbal88/PlotNeuralNet — Latex code for making neural networks diagrams
keplr-io/quiver — Interactive convnet features visualization for Keras
asappresearch/sew — SEW (Squeezed and Efficient Wav2vec) Performance-Efficiency Trade-offs in Unsupervised Pre-training for Speech Recognition
Efficient Nearest Neighbor Language Models
google/fnet-base — FNet is a transformers model with attention replaced with fourier transforms
Block Pruning For Faster Transformers
bytedance/music_source_separation
willmcgugan/rich — Rich is a Python library for rich text and beautiful formatting in the terminal.
smacke/ffsubsync — Automagically synchronize subtitles with video.
chriskiehl/Gooey — Turn (almost) any Python command line program into a full GUI application with one line
bohanli/BERT-flow — TensorFlow implementation of On the Sentence Embeddings from Pre-trained Language Models (EMNLP 2020)