YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research
• 36
AI & ML interests
voice-conversion speech-separation speech-enhancement speech-translation speech-synthesis speech-recognition spoken-language-understanding
Recent Activity
View all activity
Articles
espnet/geolid_vl107only_shared_trainable
Audio Classification • Updated • 127 • 1
espnet/geolid_vl107only_shared_frozen
Audio Classification • Updated • 148
espnet/geolid_vl107only_independent_trainable
Audio Classification • Updated • 127
espnet/geolid_vl107only_independent_frozen
Audio Classification • Updated • 120
espnet/geolid_combined_shared_trainable
Audio Classification • Updated • 123 • 1
espnet/marathi_lrec2020
Automatic Speech Recognition • Updated • 22
espnet/universa-wavlm_base_urgent24_multi-metric
Updated • 11
espnet/universa-base_urgent24_multi-metric
Updated • 17
espnet/universa-wavlm_base_urgent24_multi-metric_fullref
Updated • 18
espnet/universa-wavlm_base_urgent24_multi-metric_textref
Updated • 16
espnet/universa-wavlm_base_urgent24_multi-metric_audioref
Updated • 19
espnet/universa-wavlm_base_urgent24_multi-metric_noref
Updated • 908
espnet/arecho_scale_v0.1-large-decoder
Updated • 15
espnet/arecho_base_v0.1-large-decoder
Updated • 13
espnet/arecho_scale_v0
Updated • 18
espnet/arecho_base_v0
Updated • 24
espnet/owsm_ctc_v4_1B
Automatic Speech Recognition • Updated • 11.2k • 14
espnet/owsm_v3.1_ebf_small
Automatic Speech Recognition • Updated • 28 • 2
espnet/owsm_v3.1_ebf_base
Automatic Speech Recognition • Updated • 50 • 3
espnet/owsm_v3.1_ebf
Automatic Speech Recognition • Updated • 161 • 17
espnet/owsm_v3.1_ebf_small_lowrestriction
Automatic Speech Recognition • Updated • 16 • 3
espnet/owsm_v3
Automatic Speech Recognition • Updated • 20 • 29
espnet/owsm_v4_small_370M
Automatic Speech Recognition • Updated • 78 • 4
espnet/owsm_v4_base_102M
Automatic Speech Recognition • Updated • 182 • 1
espnet/owsm_v4_medium_1B
Automatic Speech Recognition • Updated • 119 • 6
espnet/must_c_esp2_st_train_st_conformer
Updated • 10
espnet/meld_esp2_cls_wavlm_base_plus
Updated • 20 • 1
espnet/multi-talker-whisper-small-ami
Automatic Speech Recognition • Updated • 36 • 1
espnet/anogkongda_librimix_enh_train_raw_valid.si_snr.ave
Audio-to-Audio • Updated • 17
espnet/dns_icassp21_enh_train_enh_tcn_tf_raw
Audio-to-Audio • Updated • 14