YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research
• 21
AI & ML interests
voice-conversion speech-separation speech-enhancement speech-translation speech-synthesis speech-recognition spoken-language-understanding
Recent Activity
Articles
espnet/dongwei_ami_vad_rnn
Voice Activity Detection • Updated
espnet/fastspeech2_conformer_hifigan
Audio-to-Audio • Updated • 120 • 3
espnet/brianyan918_must_c_v2_en-de_st_multidecoder
Translation • Updated • 8
espnet/simpleoier_librispeech_hubert_iter1_train_ssl_torchaudiohubert_base_960h_pretrain_it1_raw
Feature Extraction • Updated • 10
espnet/simpleoier_librispeech_hubert_iter0_train_ssl_torchaudiohubert_base_960h_pretrain_it0_raw
Feature Extraction • Updated • 9
espnet/speech_translation_mboshi_french_transformer_baseline
Translation • Updated
espnet/simpleoier_chime4_enh_asr_convtasnet_init_noenhloss_wavlm_transformer_init_raw_en_char
Automatic Speech Recognition • Updated • 8
espnet/simpleoier_chime4_enh_asr_train_enh_asr_convtasnet_fbank_transformer_raw_en_char
Automatic Speech Recognition • Updated • 8
espnet/YushiUeda_librimix_diar_enh_2_3_spk_lmf
Voice Activity Detection • Updated • 16
espnet/YushiUeda_librimix_diar_enh_2_3_spk
Voice Activity Detection • Updated • 11
espnet/brianyan918_iwslt22_dialect_train_st_conformer_ctc0.3_lr2e-3_warmup15k_newspecaug
Translation • Updated • 6 • 1
espnet/brianyan918_iwslt22_dialect_st_transformer_fisherlike_4gpu_bbins16m_fix
Translation • Updated • 8
espnet/Yushi_Ueda_mini_librispeech_diar_train_diar_raw_max_epoch20_valid.acc.best
Voice Activity Detection • Updated • 8
espnet/YushiUeda_mini_librispeech_diar_train_diar_raw_valid.acc.best
Voice Activity Detection • Updated • 11
espnet/bagpiper
Any-to-Any • Updated
espnet/bagpiper-tts-sft
Text-to-Speech • Updated
espnet/bagpiper-sft
Any-to-Any • Updated
espnet/OpenBEATS-Large-i3-as2m
Audio Classification • Updated • 10
espnet/OpenBEATS-Large-i2-as20k
Audio Classification • Updated • 16
espnet/OpenBEATS-Base-i3-as2m
Audio Classification • Updated • 12
espnet/ci_tools
Updated
espnet/powsm
Automatic Speech Recognition • Updated • 175 • 16
espnet/xeus_ckpts
Updated
espnet/mixdata_svs_visinger2_spkemb_lang_pretrained
Text-to-Audio • Updated • 18 • 1
espnet/aceopencpop_svs_visinger2_40singer_pretrain
Text-to-Audio • Updated • 22
espnet/visinger2-zh-jp-multisinger-svs
Text-to-Audio • Updated • 19
espnet/mixdata_svs_visinger2_spkemb_lang_pretrained_avg
Text-to-Audio • Updated • 2
espnet/librispeech_arkive
Updated
espnet/recipe_artifacts
Updated
espnet/mixdata_svs_visinger2_spkembed_lang_pretrained
Sentence Similarity • Updated • 6 • 1