English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Self-supervised learning (SSL) is at the origin of unprecedented improvementsin many different domains including computer vision and natural languageprocessing. Speech processing drastically benefitted from SSL as most of thecurrent domain-related tasks are now being approached with pre-trained models.This work introduces LeBenchmark 2.0 an open-source framework for assessing andbuilding SSL-equipped French speech technologies. It includes documented,large-scale and heterogeneous corpora with up to 14,000 hours of heterogeneousspeech, ten pre-trained SSL wav2vec 2.0 models containing from 26 million toone billion learnable parameters shared with the community, and an evaluationprotocol made of six downstream tasks to complement existing benchmarks.LeBenchmark 2.0 also presents unique perspectives on pre-trained SSL models forspeech with the investigation of frozen versus fine-tuned downstream models,task-agnostic versus task-specific pre-trained models as well as a discussionon the carbon footprint of large-scale model training.

LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speech