ARCH models, benchmark and paper - a morenolq Collection

morenolq 's Collections

ARCH models, benchmark and paper

ARCH models, benchmark and paper

updated Jun 21

This collection contains pre-trained models on the AudioSet dataset, offering a diverse set of features for audio representation learning.

ALM/wav2vec2-large-audioset

Audio Classification • Updated Sep 1 • 17
ALM/hubert-base-audioset

Audio Classification • Updated Sep 1 • 95 • 1
ALM/wav2vec2-base-audioset

Audio Classification • Updated Sep 1 • 6
ALM/hubert-large-audioset

Audio Classification • Updated Sep 1 • 4
Running

1

📊

ARCH

Note This space contains the results obtained using ARCH framework for pre-trained models evaluation.
Benchmarking Representations for Speech, Music, and Acoustic Events

Paper • 2405.00934 • Published May 2 • 1