Hugging Face's logo
Activity Feed

AI & ML interests

Acoustic source localization using Deep Learning, Speech enhancement, Acoustic Speech Recognition, Bandwidth extension for audio and speech, Room acoustics and RIR extrapolation / interpolation using DL, AI-based multichannel denoising ...

Recent Activity
MaloOLIVIER  updated a model about 17 hours ago
Cnam-LMSSC/wav2vec2-italian-tokenizer
MaloOLIVIER  published a model about 17 hours ago
Cnam-LMSSC/wav2vec2-italian-tokenizer
MaloOLIVIER  published a model about 18 hours ago
Cnam-LMSSC/wav2vec2-french-tokenizer
View all activity

Organization Card
Community About org cards

This is the HuggingFace hub for the AVA Team of LMSSC, at Cnam Paris (France)

Active members from the AVA team on this HuggingFace organization are :

  • Éric Bavu, Senior Researcher / Full Professor webpage
  • Louis Reine, PhD Student webpage
  • Julien Hauret, former PhD Student webpage
  • Malo Olivier, Research Engineer webpage

We propose here some of the recent pretrained models for relevant tasks in our Lab, and audio datasets, for a large dissemination.

Collections 4

VibraVox : French Speech Dataset and Models
Explore the VibraVox Dataset, pre-trained models and tools in this collection to advance research in French speech processing and related application
VibraVox : French Speech Dataset and Models
Explore the VibraVox Dataset, pre-trained models and tools in this collection to advance research in French speech processing and related application
View 4 collections