Stars
Tensors and Dynamic neural networks in Python with strong GPU acceleration
TensorFlow code and pre-trained models for BERT
Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's WaveNet and tensorflow
Speech Recognition using DeepSpeech2 network and the CTC activation function.
Script for converting kaldi GMM/HMM models to HTK format
Convert a HMM/GMM model file from HTK to Kaldi format
Ternary Gradients to Reduce Communication in Distributed Deep Learning (TensorFlow)
Protocol Buffers - Google's data interchange format
⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 instead.
PaddlePaddle High Performance Deep Learning Inference Engine for Mobile and Edge (飞桨高性能深度学习端侧推理引擎）
Fast ivector training and extraction in Kaldi using randomized SVD
Extension to Kaldi implementing the standard i-vector hyperparameter estimation and i-vector extraction procedure
Summaries and notes on Deep Learning research papers
A TensorFlow implementation of DeepMind's WaveNet paper
Collective communications library with various primitives for multi-machine training.
ncnn is a high-performance neural network inference framework optimized for the mobile platform
Deep neural networks for separating singing voice from music written in TensorFlow
A MXNet implementation of Baidu's DeepSpeech architecture
A general-purpose encoder-decoder framework for Tensorflow
Benchmarking Deep Learning operations on different hardware
Deep learning library featuring a higher-level API for TensorFlow.
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
Speech recognition software where the neural net is trained with TensorFlow and GMM training and decoding is done in Kaldi
aka "Bayesian Methods for Hackers": An introduction to Bayesian methods + probabilistic programming with a computation/understanding-first, mathematics-second point of view. All in pure Python ;)
kaldi-asr/kaldi is the official location of the Kaldi project.
The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs and GPUs using SIMD technologies.
This is now the official location of the Merlin project.