You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
simulstream is a Python library for simultaneous/streaming speech recognition and translation. It enables both the simulation with existing files to score syste…
This repository contains code used for the MCIF dataset and IWSLT 2025 Instruction Following shared task. This includes scripts used to create test sets and the…
Speech-MASSIVE is a multilingual Spoken Language Understanding (SLU) dataset comprising the speech counterpart for a portion of the MASSIVE textual corpus.
This repository contains the code associated with the Interspeech 2025 paper "Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribut…
This repository contains the code associated with the ACL2025 paper "Different Speech Translation Models Encode and Translate Speaker Gender Differently".
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.