6
ARCH
📊
Compare audio representation models
ARCH models, benchmark and paper
This collection contains pre-trained models on the AudioSet dataset, offering a diverse set of features for audio representation learning.
Note This space contains the results obtained using ARCH framework for pre-trained models evaluation.
-
ALM/wav2vec2-large-audioset
Audio Classification • 0.3B • Updated • 98 • 1 -
ALM/hubert-base-audioset
Audio Classification • Updated • 251 • 3 -
ALM/wav2vec2-base-audioset
Audio Classification • Updated • 793 • 1 -
ALM/hubert-large-audioset
Audio Classification • Updated • 56 -
Benchmarking Representations for Speech, Music, and Acoustic Events
Paper • 2405.00934 • Published • 1