Skip to content

@BUTSpeechFIT BUT Speech@FIT

Change the repository type filter

All

    Repositories list

    57 repositories

    • FLiP

      Public
      Factorized Linear Projection for Interpreting Multilingual and Multimodal Sentence Embeddings
      Python
      •
      Other
      •0•0•0•0•Updated Apr 20, 2026Apr 20, 2026

    • DiariZen

      Public
      A toolkit for speaker diarization.
      Jupyter Notebook
      •
      MIT License
      •50•442•5•1•Updated Apr 9, 2026Apr 9, 2026

    • TS-ASR-Whisper

      Public
      Python
      •
      Apache License 2.0
      •14•106•0•0•Updated Mar 1, 2026Mar 1, 2026

    • mt-asr-data-prep

      Public
      Shell
      •1•21•0•0•Updated Feb 26, 2026Feb 26, 2026

    • CHiME-9-AV-TS-ASR

      Public
      This repository contains the implementation of our CHiME-9 AV-TS-ASR pipeline.
      0•4•0•0•Updated Feb 16, 2026Feb 16, 2026

    • besst-dataset

      Public
      BESST dataset
      Python
      •0•1•0•0•Updated Jan 29, 2026Jan 29, 2026

    • DiCoW

      Public
      Python
      •
      Apache License 2.0
      •12•92•2•1•Updated Jan 28, 2026Jan 28, 2026

    • NAC-LD-Endpointer

      Public
      Codebase for the work "Streaming Endpointer for Spoken Dialogue using Neural Audio Codecs and Label-Delayed Training", accepted at ASRU 2025
      Python
      •
      Apache License 2.0
      •0•8•0•0•Updated Dec 17, 2025Dec 17, 2025

    • ORCA

      Public
      Open-ended Response Correctness Assessment for Audio Question Answering
      Python
      •
      MIT License
      •0•3•0•0•Updated Dec 9, 2025Dec 9, 2025

    • MultiWOZ_Evaluation

      Public
      Unified MultiWOZ evaluation scripts for the context-to-response task.
      Python
      •
      MIT License
      •13•0•0•0•Updated Dec 5, 2025Dec 5, 2025

    • USE_DDP

      Public
      Official implementation of Unsupervised Speech Enhancement using Data-Defined Priors.
      0•9•0•0•Updated Nov 10, 2025Nov 10, 2025

    • SOT-DiCoW

      Public
      Multi-talker ASR based on DiCoW with Serialized Output Training
      Python
      •
      Apache License 2.0
      •3•18•2•0•Updated Sep 18, 2025Sep 18, 2025

    • DeCRED

      Public
      Jupyter Notebook
      •
      Apache License 2.0
      •0•18•0•0•Updated Aug 13, 2025Aug 13, 2025

    • huggingface_asr

      Public
      Extensions of huggingface library for e2e speech recognition.
      Python
      •1•8•9•1•Updated Jul 7, 2025Jul 7, 2025

    • EEND

      Public
      Python
      •13•95•2•0•Updated Apr 24, 2025Apr 24, 2025

    • TS_SUPERB

      Public
      Python
      •
      Apache License 2.0
      •1•15•0•0•Updated Apr 2, 2025Apr 2, 2025

    • EEND_dataprep

      Public
      Shell
      •10•59•1•0•Updated Mar 28, 2025Mar 28, 2025

    • OLMo

      Public
      Modeling, training, eval, and inference code for OLMo
      Python
      •
      Apache License 2.0
      •751•1•0•0•Updated Feb 5, 2025Feb 5, 2025

    • MultiSV

      Public
      MultiSV: scripts for data preparation
      Shell
      •3•30•0•0•Updated Jan 18, 2025Jan 18, 2025

    • safe_gpu

      Public
      Avoids race condition when acquiring GPUs in exclusive mode
      Python
      •
      MIT License
      •2•20•1•0•Updated Nov 11, 2024Nov 11, 2024

    • error_correction_playground

      Public
      HTML
      •0•0•0•0•Updated Oct 4, 2024Oct 4, 2024

    • CHiME-8_NOTSOFAR-1

      Public
      CHiME-8 NOTSOFAR-1
      0•1•0•0•Updated Oct 2, 2024Oct 2, 2024

    • EENDEDA_VIB

      Public
      Python
      •
      MIT License
      •1•6•0•0•Updated Sep 24, 2024Sep 24, 2024

    • DVBx

      Public
      Discriminative Training of VBx Diarization
      Python
      •
      MIT License
      •2•27•1•0•Updated Sep 23, 2024Sep 23, 2024

    • wespeaker_ssl_public

      Public
      Using Pre-trained SSL Transformer Models for Speaker Verification
      Python
      •
      Apache License 2.0
      •1•9•0•0•Updated Sep 22, 2024Sep 22, 2024

    • wespeaker_public

      Public
      Research and Production Oriented Speaker Verification, Recognition and Diarization Toolkit
      Python
      •
      Apache License 2.0
      •190•1•0•0•Updated Sep 17, 2024Sep 17, 2024

    • Wespeaker_MC_SSL

      Public
      Multi-channel SV with pre-trained SSL models
      Python
      •
      Apache License 2.0
      •0•4•0•0•Updated Sep 2, 2024Sep 2, 2024

    • diarization_utils

      Public
      Python
      •2•12•0•0•Updated Jul 30, 2024Jul 30, 2024

    • espnet

      Public
      A clone of ESPnet toolkit. Not all recent changes in original ESPnet are reflected here.
      Python
      •
      Apache License 2.0
      •0•0•0•0•Updated May 14, 2024May 14, 2024

    • BaySMM

      Public
      A Bayesian Multilingual Document Model
      multilingualtopicembeddings
      multilingualtopicembeddingsclassificationdocumentbayesian
      Python
      •4•9•0•0•Updated Mar 23, 2024Mar 23, 2024
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.