MoLE : Mixture of Language Experts for Multi-Lingual Automatic Speech Recognition
Paper
•
2302.13750
•
Published
•
2
Low-resource ASR models
-
-
Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition
Paper • 2204.03855 • Published -
Improving Massively Multilingual ASR With Auxiliary CTC Objectives
Paper • 2302.12829 • Published -
espnet/wanchichen_fleurs_asr_conformer_hier_lid_utt
Automatic Speech Recognition • Updated • 4 • 2 -
espnet/wanchichen_fleurs_asr_conformer_scctc
Updated • 1 -
espnet/wanchichen_fleurs_multilingual_asr_hubert_frontend
Updated • 8 • 2 -
espnet/wanchichen_fleurs_english_asr_wav2vec_frontend
Updated • 2 • 1