FBK-SpeechTek

SpeechTek's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

seraphina 

updated 3 models 2 days ago

SpeechTek/MEUSLI_projector_v2_Apertus_8B_Instruct

Automatic Speech Recognition • Updated 2 days ago • 2

SpeechTek/MEUSLI_projector_v2

Automatic Speech Recognition • Updated 2 days ago • 5

SpeechTek/mEUltilingual_speechllm_linear_projector_v1

Automatic Speech Recognition • Updated 2 days ago • 5

lorenzoncina 

published a model 11 days ago

SpeechTek/MEUSLI_projector_v2_Apertus_8B_Instruct

Automatic Speech Recognition • Updated 2 days ago • 2

lorenzoncina 

updated 3 models 11 days ago

SpeechTek/MEUSLI_projector_v2_Villanova_2B

Updated 11 days ago • 3

SpeechTek/MEUSLI_projector_v2_Apertus_8B_Instruct

Automatic Speech Recognition • Updated 2 days ago • 2

SpeechTek/MEUSLI_projector_v2

Automatic Speech Recognition • Updated 2 days ago • 5

lorenzoncina 

published a model 3 months ago

SpeechTek/MEUSLI_projector_v2_Villanova_2B

Updated 11 days ago • 3

lorenzoncina 

updated a collection 3 months ago

mEUltilingual speechLLM projectors

Collection

Multilingual projectors trained with SLAM-ASR for EU languages. • 4 items • Updated 2 days ago • 5

falavi 

updated 2 models 4 months ago

SpeechTek/Italian-EE-conformer

Updated Apr 14

SpeechTek/English-EE-conformer

Updated Apr 14

mnabihali 

authored 2 papers 10 months ago

MLMA: Towards Multilingual with Mamba Based Architectures

Paper • 2510.18684 • Published Oct 21, 2025

Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients

Paper • 2405.17376 • Published May 27, 2024 • 1

lorenzoncina 

updated a collection 11 months ago

mEUltilingual speechLLM projectors

Collection

Multilingual projectors trained with SLAM-ASR for EU languages. • 4 items • Updated 2 days ago • 5

falavi 

authored 5 papers 11 months ago

Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

Paper • 2309.09546 • Published Sep 18, 2023 • 1

Continual Contrastive Spoken Language Understanding

Paper • 2310.02699 • Published Oct 4, 2023

Sequence-Level Knowledge Distillation for Class-Incremental End-to-End Spoken Language Understanding

Paper • 2305.13899 • Published May 23, 2023

Mixtures of Deep Neural Experts for Automated Speech Scoring

Paper • 2106.12475 • Published Jun 23, 2021 • 1

Efficient Fine-tuning of Audio Spectrogram Transformers via Soft Mixture of Adapters

Paper • 2402.00828 • Published Feb 1, 2024