The goal of the project is to provide machine learning for everyone, both technical and non-technical users. I needed a tool sometimes, which I can use to fast create a machine learning prototype. Whether to build some proof of concept or create a fast draft model to prove a point. I find myself often stuck at writing boilerplate code and/or thinking too much of how to start this.
data-science machine-learning automation neural-network scikit-learn sklearn machine-learning-algorithms artificial-intelligence neural-networks data-analysis machine-learning-library machinelearning preprocessing automl multilayer-perceptron-network scikitlearn-machine-learning multilayer-perceptron automl-api automl-algorithms automl-experimentsThis code implements a basic MLP for HMM-DNN speech recognition. The MLP is trained with pytorch, while feature extraction, alignments, and decoding are performed with Kaldi. The current implementation supports dropout and batch normalization. An example for phoneme recognition using the standard TIMIT dataset is provided. Make sure that python is installed (the code is tested with python 2.7). Even though not mandatory, we suggest to use Anaconda (https://anaconda.org/anaconda/python).
pytorch asr kaldi deep-learning deep-neural-networks speech-recognition timit mlp feedforward-neural-network kaldi-asr multilayer-perceptron neural-networks cudaLow dependency(C++11 STL only), good portability, header-only, deep neural networks for embedded
deep-learning back-propagation cross-entropy multilayer-perceptron data-visualization data-scienceA micro neural network multilayer perceptron for MicroPython (used on ESP32 and Pycom modules)
machine-learning qlearning ai deep-learning neural-network micropython esp32 q-learning artificial-intelligence neurons deeplearning mlp predictive-modeling ann lopy wipy pycom multilayer-perceptron hc2
We have large collection of open source products. Follow the tags from
Tag Cloud >>
Open source products are scattered around the web. Please provide information
about the open source projects you own / you use.
Add Projects.