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/su_openslr36
Automatic Speech Recognition • Updated • 10
espnet/simpleoier_librispeech_asr_train_asr_conformer7_wavlm_large_raw_en_bpe5000_sp
Automatic Speech Recognition • Updated • 12 • 1
espnet/simpleoier_librispeech_asr_train_asr_conformer7_wav2vec2_960hr_large_raw_en_bpe5000_sp
Automatic Speech Recognition • Updated • 7
espnet/siddhana_slurp_new_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best
Automatic Speech Recognition • Updated • 12
espnet/simpleoier_librispeech_asr_train_asr_conformer7_hubert_ll60k_large_raw_en_bpe5000_sp
Automatic Speech Recognition • Updated • 10 • 2
espnet/siddhana_slurp_entity_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best
Automatic Speech Recognition • Updated • 8
espnet/siddhana_slue_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best
Automatic Speech Recognition • Updated • 8
espnet/siddhana_fsc_unseen_asr_train_asr_hubert_transformer_adam_specaug_fine-truncated-ef9dab
Automatic Speech Recognition • Updated • 8
espnet/siddhana_fsc_challenge_asr_train_asr_hubert_transformer_adam_specaug_r-truncated-36174d
Automatic Speech Recognition • Updated • 6
espnet/siddhana_fsc_asr_train_asr_hubert_transformer_adam_specaug_raw_en_word_valid.acc.ave_5best
Automatic Speech Recognition • Updated • 7
espnet/roshansh_how2_asr_raw_ft_sum_valid.acc
Automatic Speech Recognition • Updated • 14
espnet/shinji-watanabe-librispeech_asr_train_asr_transformer_e18_raw_bpe_sp_valid.acc.best
Automatic Speech Recognition • Updated • 9
espnet/pengcheng_guo_wenetspeech_asr_train_asr_raw_zh_char
Automatic Speech Recognition • Updated • 13 • 12
espnet/kan_bayashi_jsut_tts_train_conformer_fastspeech2_raw_phn_jaconv_pyopenjtalk_train.loss.ave
Text-to-Speech • Updated • 7 • 1
espnet/kan-bayashi_vctk_xvector_transformer
Text-to-Speech • Updated • 6
espnet/kan-bayashi_vctk_xvector_conformer_fastspeech2
Text-to-Speech • Updated • 9
espnet/kan-bayashi_vctk_xvector_tacotron2
Text-to-Speech • Updated • 8
espnet/kan-bayashi_vctk_tts_train_xvector_transformer_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
Text-to-Speech • Updated • 9
espnet/kan-bayashi_vctk_tts_train_xvector_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
Text-to-Speech • Updated • 8
espnet/kan-bayashi_vctk_tts_train_xvector_conformer_fastspeech2_transformer_t-truncated-69a657
Text-to-Speech • Updated • 9
espnet/kan-bayashi_vctk_tts_train_gst_xvector_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
Text-to-Speech • Updated • 11
espnet/kan-bayashi_vctk_tts_train_multi_spk_vits_raw_phn_tacotron_g2p_en_no_space_train.total_count.ave
Text-to-Speech • Updated • 5
espnet/kan-bayashi_vctk_tts_train_gst_xvector_conformer_fastspeech2_transform-truncated-e051a9
Text-to-Speech • Updated • 9
espnet/kan-bayashi_vctk_tts_train_gst_transformer_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
Text-to-Speech • Updated • 5
espnet/kan-bayashi_vctk_tts_train_gst_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.best
Text-to-Speech • Updated • 7
espnet/kan-bayashi_vctk_tts_train_gst_fastspeech2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave
Text-to-Speech • Updated • 6
espnet/kan-bayashi_vctk_tts_train_gst_fastspeech_raw_phn_tacotron_g2p_en_no_space_train.loss.best
Text-to-Speech • Updated • 7
espnet/kan-bayashi_vctk_tts_train_gst_conformer_fastspeech2_raw_phn_tacotron_-truncated-69081b
Text-to-Speech • Updated • 7
espnet/kan-bayashi_vctk_tts_train_full_band_multi_spk_vits_raw_phn_tacotron_g-truncated-50b003
Text-to-Speech • Updated • 12 • 1
espnet/kan-bayashi_vctk_multi_spk_vits
Text-to-Speech • Updated • 27