Make text LLMs listen and speak

Codebase for the work "Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training", accepted at ASRU 2025

Self-Supervised Speech Pre-training and Representation Learning Toolkit

A set of demo applications that make use of google speech, nlp and vision apis based in angular2

The fastai deep learning library

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Socket.IO integration for Flask applications.

Gathers Python deployment, infrastructure and practices.

PyTorch re-implementation of Grad-CAM (+ vanilla/guided backpropagation, deconvnet, and occlusion sensitivity maps)

Pytorch implementation of convolutional neural network visualization techniques

Text Similarity

Neat (Neural Attention) Vision, is a visualization tool for the attention mechanisms of deep-learning models for Natural Language Processing (NLP) tasks. (framework-agnostic)

Implementation of State-of-the-art Text Classification Models in Pytorch

Text classification using deep learning models in Pytorch

A game theoretic approach to explain the output of any machine learning model.

Directions overlay for working with pandas in an analysis environment

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Code for YouTube series: Deep Learning for Audio Classification

Official Tensorflow implementation of U-GAT-IT: Unsupervised Generative Attentional Networks with Adaptive Layer-Instance Normalization for Image-to-Image Translation (ICLR 2020)

Python Audio Analysis Library: Feature Extraction, Classification, Segmentation and Applications

Analyzes signal, finds fundamental frequency, HNR etc

Praat in Python, the Pythonic way

Voice Activity Detector in Python

This project is a tool to build CheXNet-like models, written in Keras.