A curated list of interpretability work for speech processing models

This repository contains all the code for the works of the FBK MT Unit on foundation models and LLMs.

PyTorch native post-training library

Collection of Open Source Speech Data

Repository containing the open source code of works published at the FBK MT unit.

Speech-MASSIVE is a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSIVE textual corpus.

As a Pangolin looks for bugs and catches them, the goal of this library is ot help developers finding bugs in their neural networks and newly-created models.

Evaluate the quality of SRT files using the multilingual multimodal SONAR model.

Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

Profiling and inspecting memory in pytorch

Low-code framework for building custom LLMs, neural networks, and other AI models

Examples to run Hadoop/Spark clusters locally with docker-compose.

DBSCAN clustering algorithm on top of Apache Spark