Stars
An open, scalable, online streaming setup. All-in-one toolkit from ingest to adaptive video playback. Built for developers in need of video tooling.
A reactive notebook for Python — run reproducible experiments, query with SQL, execute as a script, deploy as an app, and version with git. Stored as pure Python. All in a modern, AI-native editor.
A tool for converting ONNX files to LiteRT/TFLite/TensorFlow, PyTorch native code (nn.Module), TorchScript (.pt), state_dict (.pt), Exported Program (.pt2), and Dynamo ONNX. It also supports direct…
Keras beit,caformer,CMT,CoAtNet,convnext,davit,dino,efficientdet,edgenext,efficientformer,efficientnet,eva,fasternet,fastervit,fastvit,flexivit,gcvit,ghostnet,gpvit,hornet,hiera,iformer,inceptionne…
This is a list of interesting papers and projects about TinyML.
PyTorch and TensorFlow implementation of NCP, LTC, and CfC wired neural models
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
YoloV3 Implemented in Tensorflow 2.0
Forced Alignments for Common Voice
Infrastructure to enable deployment of ML models to low-power resource-constrained embedded targets (including microcontrollers and digital signal processors).
A Keras port of Single Shot MultiBox Detector
A dataset of chicken vocalizations intended to create a machine learning model for chicken to human language translation
SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
Parse TFLite models (*.tflite) EASILY with Python. Check the API at https://zhenhuaw.me/tflite/docs/
generate tflite micro code which bypasses the interpreter (directly calls into kernels)
A collection of resources for the hobbyists, students, teachers, and makers who want to develop professional-grade embedded systems but who lack the resources of a commercial enterprise.
Keras implementation of musicnn, a set of pre-trained deep convolutional neural networks for music audio tagging
Command line utility to display various high level information about a TFlite model flatbuffer
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
The Microsoft Scalable Noisy Speech Dataset (MS-SNSD) is a noisy speech dataset that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) l…
Manipulate audio with a simple and easy high level interface