Adapting ASR system using LoRA, based on the speaker. For customized model weights per-person.Project fro CSC2518 Spoken Language Processing at UofT.

"Brian Hears" auditory modelling toolbox for the brian2 simulator

Code and data for Koenecke et al. (2020)

This is an open source project (formerly named Listen, Attend and Spell - PyTorch Implementation) for end-to-end ASR implemented with Pytorch, the well known deep learning toolkit.

The RWTH extensible training framework for universal recurrent neural networks

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

Collection of tools and code examples to demonstrate best practices in using Amazon EC2 Spot Instances.

An implementation of the Contrast Predictive Coding (CPC) method to train audio features in an unsupervised fashion.

A helper tool for running array jobs on an HPC computational node.

Simple Minimalistic Theme for Hugo

Theme for the Hugo static website generator

A Python package of the dynamic compressive gammachirp filterbank (dcGC-FB)

A PyTorch repo for data loading and utilities to be shared by the PyTorch domain libraries.

University of Toronto thesis class for LaTeX

Examples scripts that showcase how to use Private AI Text to de-identify, redact, hash, tokenize, mask and synthesize PII in text.

SoundFile is an audio library based on libsndfile, CFFI, and NumPy

Full-speed Array of Structures access

The first realistic and public dataset with rare undesirable real events in oil wells.

Seamless operability between C++11 and Python

A conda-smithy repository for faiss-split.

Real-time Web Dashboard for Optuna.

Evaluate your speech-to-text system with similarity measures such as word error rate (WER)

Automatically exported from code.google.com/p/aimc

🎡 Build Python wheels for all the platforms with minimal configuration.

Boost LaTeX typesetting efficiency with preview, compile, autocomplete, colorize, and more.

A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain

Full Python implementation of the ROUGE metric, producing same results as in the official perl implementation.

Pytorch implementation of sparse_image_warp and an example of GoogleBrain's SpecAugment is given: A Simple Data Augmentation Method for Automatic Speech Recognition https://arxiv.org/abs/1904.08779

🔦 A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition