YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research about 23 hours ago • 15
espnet/kan-bayashi_ljspeech_joint_finetune_conformer_fastspeech2_hifigan Text-to-Speech • Updated Oct 23, 2021 • 6 • 16
espnet/byan_librispeech_asr_train_asr_conformer_raw_bpe_batch_bins30000000_ac-truncated-68a97b Automatic Speech Recognition • Updated Sep 1, 2021