Software

FBK-Fairseq

by Marco Gaido | May 17, 2024 | Software | 0

Open source repository with the code and models used in recent papers

SubSONAR

by Marco Gaido | May 17, 2024 | Software | 0

SubSONAR evaluates the quality of SRT files using the multilingual multimodal SONAR model. The evaluation accounts for the semantic similarity (computed as a cosine similarity) between each subtitle block and the corresponding...

pangolinn

by Marco Gaido | May 17, 2024 | Software | 0

pangolinn is a Python library for neural network developers that contains test suites aimed at...

ModernMT

by Matteo Negri | May 30, 2023 | Software | 0

A neural adaptive machine translation system that adapts to context and learns from corrections

AQET

by Dennis Fucci | May 30, 2023 | Software | 0

AQET (Adaptive Quality Estimation Tool) is an open-source package for performing Quality Estimation for Machine Translation able to continuously learn from post-edited sentences.

onlineMGIZA++

by Andrea Piergentili | May 30, 2023 | Software | 0

An extension of MGIZA++, which allows to align sentence pair in an online mode.

IRSTLM

by Dennis Fucci | May 30, 2023 | Software | 0

The IRST Language Modeling (IRSTLM) Toolkit features algorithms and data structures suitable to estimate, store, and access very large n-gram language models.

MOSES

by Dennis Fucci | May 30, 2023 | Software | 0

Moses is a statistical machine translation system that allows you to automatically train translation models for any language pair.

MT Group at FBK Follow

#MachineTranslation Research Unit @FBK_research. #nlproc #deeplearning #ai

Retweet on Twitter MT Group at FBK Retweeted

Avatar Sara Papi @sarapapi ·

30 May

🚀 New tech report out! Meet FAMA, our open-science speech foundation model family for both ASR and ST in 🇬🇧 English and 🇮🇹 Italian.

The models are live and ready to try on @huggingface 👇
🔗

#ASR #ST #OpenScience #MultilingualAI

Reply on Twitter 1928375820650684427 Retweet on Twitter 1928375820650684427 10 Like on Twitter 1928375820650684427 24 Twitter 1928375820650684427

Avatar MT Group at FBK @fbk_mt ·

29 May

Our pick of the week by @lina_conti: "Languages in Multilingual Speech Foundation Models Align Both Phonetically and Semantically" by @soheunshim, Domenico De Cristofaro, Chengzhi Martin Hu, Alessandro Vietti, and @barbara_plank (2025).

#speech #SFM #multilingual #speechtech

Lina Conti @lina_conti

Pick of the week @fbk_mt: https://arxiv.org/abs/2505.19606 by @soheunshim @DomenicoDeCris1. XAI work on cross-lingual alignment in speech-to-text models that disentangles phonetics and semantics. Plus: their XAI insights yield actionable improvements for low-resource language performance.

Reply on Twitter 1928123128753897811 Retweet on Twitter 1928123128753897811 1 Like on Twitter 1928123128753897811 7 Twitter 1928123128753897811

Retweet on Twitter MT Group at FBK Retweeted

Avatar Marco Gaido @mgaido91 ·

26 May

🚀 New shared task at #WMT2025 (co-located with @emnlpmeeting ): Model Compression for Machine Translation!
Can you shrink an LLM and keep translation quality high?🔧
Submit by July 3 and push the limits of efficient NLP!
👉 https://www2.statmt.org/wmt25/model-compression.html #NLP #ML #LLM #ModelCompression

Reply on Twitter 1926917384633266349 Retweet on Twitter 1926917384633266349 11 Like on Twitter 1926917384633266349 10 Twitter 1926917384633266349

Retweet on Twitter MT Group at FBK Retweeted

Avatar Dennis Fucci @dennisfucci ·

19 May

More great news! 🎉
Our paper “Echoes of Phonetics: Unveiling Relevant Acoustic Cues for ASR via Feature Attribution” was accepted at #Interspeech2025!

Interested in interpretability for speech models? Preprint coming soon!

✍🏼 @mgaido91, @negri_teo, M.Cettolo, @luisabentivogli

Reply on Twitter 1924501980564652370 Retweet on Twitter 1924501980564652370 6 Like on Twitter 1924501980564652370 15 Twitter 1924501980564652370