A scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)

Inference code for CodeLlama models

A PyTorch-based Speech Toolkit

Author's repository for reproducing RawNet 1 and 2 papers with pre-trained model weights and speaker embeddings. RawNet2 is implemented in PyTorch and RawNet1 is implemented in PyTorch and Keras.

Scikit-Learn, NLTK, Spacy, Gensim, Textblob and more

Tensorflow 2.x implementation of the DTLN real time speech denoising model. With TF-lite, ONNX and real-time audio processing support.

Implementation of MOS-transformation to be used with Rank based statistical techniques.

Visualizer for neural network, deep learning and machine learning models

Aggregate multiple tensorboard runs to new summary or csv files

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate

A Python library that implements software engineering best-practice for data and ML pipelines.

Set of utils for Ubuntu. Useful when setting up a new machine.

Cheatsheet to remember some of the most useful shorcuts in Vim.

GPU accelerated implementation of i-vector extractor training using PyTorch. Requires Kaldi for feature extraction and UBM training. An example script is provided for VoxCeleb data.

Performance-optimized wheels for TensorFlow (SSE, AVX, FMA, XLA, MPI)

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

all kinds of audio format convert to wav

Pytorch implementation of Center Loss

Squeeze-and-Excitation Networks

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://nervanasystems.github.io/distiller

Cat-and-Mouse game with Reinforcement Learning (Q-Learning).

Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)

Collection of useful FFMPEG commands for processing audio and video files.

Finding Direction of arrival (DOA) of small UAVs using Sparse Denoising Autoencoders and Deep Neural Networks.

Implementation of triplet loss in TensorFlow

Local Binary Convolutional Neural Networks by pytorch

A curated list of awesome resources related to capsule networks

Siamese and triplet networks with online pair/triplet mining in PyTorch

A parser for Google Scholar, written in Python