YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research
• 1
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/kan-bayashi_vctk_gst_xvector_tacotron2
Text-to-Speech • Updated • 7
espnet/kan-bayashi_vctk_gst_xvector_transformer
Text-to-Speech • Updated • 7
espnet/kan-bayashi_vctk_gst_xvector_conformer_fastspeech2
Text-to-Speech • Updated • 6
espnet/kan-bayashi_vctk_gst_transformer
Text-to-Speech • Updated • 7
espnet/kan-bayashi_vctk_gst_fastspeech2
Text-to-Speech • Updated • 6
espnet/kan-bayashi_vctk_gst_tacotron2
Text-to-Speech • Updated • 7
espnet/kan-bayashi_vctk_gst_fastspeech
Text-to-Speech • Updated • 8
espnet/kan-bayashi_vctk_gst_conformer_fastspeech2
Text-to-Speech • Updated • 5
espnet/kan-bayashi_vctk_full_band_multi_spk_vits
Text-to-Speech • Updated • 7 • 2
espnet/kan-bayashi_tsukuyomi_tts_finetune_full_band_jsut_vits_raw_phn_jaconv_pyopenjtalk_prosody_latest
Text-to-Speech • Updated • 7 • 3
espnet/kan-bayashi_tsukuyomi_full_band_vits_prosody
Text-to-Speech • Updated • 22 • 3
espnet/kan-bayashi_ljspeech_vits
Text-to-Speech • Updated • 90 • 226
espnet/kan-bayashi_ljspeech_tts_train_vits_raw_phn_tacotron_g2p_en_no_space_train.total_count.ave
Text-to-Speech • Updated • 7
espnet/kan-bayashi_ljspeech_tts_train_transformer_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
Text-to-Speech • Updated • 14
espnet/kan-bayashi_ljspeech_tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.best
Text-to-Speech • Updated • 7
espnet/kan-bayashi_ljspeech_tts_train_fastspeech_raw_phn_tacotron_g2p_en_no_space_train.loss.best
Text-to-Speech • Updated • 7
espnet/kan-bayashi_ljspeech_tts_train_joint_conformer_fastspeech2_hifigan_raw-truncated-af8fe0
Text-to-Speech • Updated • 5 • 3
espnet/kan-bayashi_ljspeech_tts_train_fastspeech2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
Text-to-Speech • Updated • 14 • 1
espnet/kan-bayashi_ljspeech_tts_train_conformer_fastspeech2_raw_phn_tacotron_-truncated-ec9e34
Text-to-Speech • Updated • 7
espnet/kan-bayashi_ljspeech_tts_finetune_joint_conformer_fastspeech2_hifigan_-truncated-737899
Text-to-Speech • Updated • 12 • 1
espnet/kan-bayashi_ljspeech_transformer
Text-to-Speech • Updated • 11
espnet/kan-bayashi_ljspeech_tacotron2
Text-to-Speech • Updated • 12 • 3
espnet/kan-bayashi_ljspeech_joint_train_conformer_fastspeech2_hifigan
Text-to-Speech • Updated • 11
espnet/kan-bayashi_ljspeech_fastspeech
Text-to-Speech • Updated • 13
espnet/kan-bayashi_ljspeech_fastspeech2
Text-to-Speech • Updated • 21
espnet/kan-bayashi_ljspeech_conformer_fastspeech2
Text-to-Speech • Updated • 16 • 1
espnet/kan-bayashi_libritts_xvector_vits
Text-to-Speech • Updated • 16
espnet/kan-bayashi_libritts_xvector_conformer_fastspeech2
Text-to-Speech • Updated • 14
espnet/kan-bayashi_libritts_xvector_trasnformer
Text-to-Speech • Updated • 9
espnet/kan-bayashi_libritts_tts_train_xvector_vits_raw_phn_tacotron_g2p_en_no-truncated-09d645
Text-to-Speech • Updated • 12