Lists (9)
Starred repositories
50
stars
written in Jupyter Notebook
Clear filter
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
Reference models and tools for Cloud TPUs.
Dealing with all unstructured data, such as reverse image search, audio search, molecular search, video analysis, question and answer systems, NLP, etc.
Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".
Demonstrations of Magenta Models
kinivi / hand-gesture-recognition-mediapipe
Forked from Kazuhito00/hand-gesture-recognition-using-mediapipeThis is a sample program that recognizes hand signs and finger gestures with a simple MLP using the detected key points. Handpose is estimated using MediaPipe.
MediaPipe(Python版)を用いて手の姿勢推定を行い、検出したキーポイントを用いて、簡易なMLPでハンドサインとフィンガージェスチャーを認識するサンプルプログラムです。（Estimate hand pose using MediaPipe(Python version). This is a sample program that recognizes hand signs and…
ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the u…
OpenL3: Open-source deep audio and image embeddings
Cleora AI is a general-purpose open-source model for efficient, scalable learning of stable and inductive entity embeddings for heterogeneous relational data. Created by Synerise.com team.
[SIGGRAPH Asia 2022] IDE-3D: Interactive Disentangled Editing For High-Resolution 3D-aware Portrait Synthesis
borb is a library for reading, creating and manipulating PDF files in python.
Software defined LaserDisc decoder
Machine Learning applied to sound
Maps that show time instead of space
Learn and L3 embedding from audio/video pairs
This repository contains Natural Language Generation (NLG) models aimed on generating text of fairy tales (Markov Chain, LSTM neural network, GPT-2 Transformers).
python scripts for signing, packaging, notarizing and stapling command line binaries
New Algorithms for Learning on Hypergraphs
Procedural 3D Terrain Generation using Generative Adversarial Networks
MIDI2vec computes embeddings for representing MIDI data in vector space
Learning to represent shortest paths and other graph-based measures of node similarities with graph embeddings
US utility patent similarity data creation and analysis tools