ESPnet

non-profit

https://github.com/espnet/espnet

espnet

AI & ML interests

voice-conversion speech-separation speech-enhancement speech-translation speech-synthesis speech-recognition spoken-language-understanding

Recent Activity

wanchichen new activity about 2 hours ago

espnet/yodas:Update README.md

cjli authored a paper 9 days ago

Prompt-MII: Meta-Learning Instruction Induction for LLMs

cjli authored a paper 9 days ago

POWSM: A Phonetic Open Whisper-Style Speech Foundation Model

View all activity

espnet 's models 653

espnet/Karthik_sinhala_asr_train_asr_transformer

Automatic Speech Recognition • Updated Jan 8, 2022 • 2

espnet/siddhana_slue_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best

Automatic Speech Recognition • Updated Dec 28, 2021

espnet/ftshijt_espnet2_asr_totonac_transformer

Automatic Speech Recognition • Updated Dec 21, 2021

espnet/ftshijt_espnet2_asr_yolo_mixtec_transformer

Automatic Speech Recognition • Updated Dec 21, 2021

espnet/ftshijt_espnet2_asr_puebla_nahuatl_transfer

Automatic Speech Recognition • Updated Dec 21, 2021

espnet/kan-bayashi_csj_asr_train_asr_conformer

Automatic Speech Recognition • Updated Nov 25, 2021 • 2 • 1

espnet/siddhana_fsc_challenge_asr_train_asr_hubert_transformer_adam_specaug_r-truncated-36174d

Automatic Speech Recognition • Updated Nov 12, 2021 • 1

espnet/siddhana_fsc_unseen_asr_train_asr_hubert_transformer_adam_specaug_fine-truncated-ef9dab

Automatic Speech Recognition • Updated Nov 12, 2021 • 1

espnet/siddhana_slurp_entity_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best

Automatic Speech Recognition • Updated Nov 6, 2021 • 1

espnet/pengcheng_guo_wenetspeech_asr_train_asr_raw_zh_char

Automatic Speech Recognition • Updated Oct 27, 2021 • 4 • 12

espnet/siddhana_slurp_new_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best

Automatic Speech Recognition • Updated Oct 25, 2021

espnet/siddhana_fsc_asr_train_asr_hubert_transformer_adam_specaug_raw_en_word_valid.acc.ave_5best

Automatic Speech Recognition • Updated Oct 25, 2021 • 1

espnet/kan-bayashi_ljspeech_joint_finetune_conformer_fastspeech2_hifigan

Text-to-Speech • Updated Oct 23, 2021 • 3 • 16

espnet/kan-bayashi_ljspeech_joint_train_conformer_fastspeech2_hifigan

Text-to-Speech • Updated Oct 23, 2021 • 2

espnet/kan-bayashi_ljspeech_tts_finetune_joint_conformer_fastspeech2_hifigan_-truncated-737899

Text-to-Speech • Updated Oct 23, 2021 • 2 • 1

espnet/kan-bayashi_ljspeech_tts_train_joint_conformer_fastspeech2_hifigan_raw-truncated-af8fe0

Text-to-Speech • Updated Oct 23, 2021 • 1 • 3

espnet/kan-bayashi_libritts_xvector_vits

Text-to-Speech • Updated Oct 23, 2021 • 11

espnet/kan-bayashi_libritts_tts_train_xvector_vits_raw_phn_tacotron_g2p_en_no-truncated-09d645

Text-to-Speech • Updated Oct 23, 2021

espnet/kan-bayashi_tsukuyomi_full_band_vits_prosody

Text-to-Speech • Updated Oct 23, 2021 • 1 • 3

espnet/kan-bayashi_tsukuyomi_tts_finetune_full_band_jsut_vits_raw_phn_jaconv_pyopenjtalk_prosody_latest

Text-to-Speech • Updated Oct 23, 2021 • 2 • 3

espnet/kan-bayashi_jvs_jvs010_vits_prosody

Text-to-Speech • Updated Oct 23, 2021 • 2

espnet/kan-bayashi_jvs_tts_finetune_jvs010_jsut_vits_raw_phn_jaconv_pyopenjtalk_prosody_latest

Text-to-Speech • Updated Oct 23, 2021 • 1

espnet/kan-bayashi_jsut_full_band_vits_prosody

Text-to-Speech • Updated Oct 23, 2021 • 11

espnet/kan-bayashi_jsut_vits_prosody

Text-to-Speech • Updated Oct 23, 2021 • 6

espnet/kan-bayashi_jsut_tts_train_full_band_vits_raw_phn_jaconv_pyopenjtalk_p-truncated-66d5fc

Text-to-Speech • Updated Oct 23, 2021 • 1

espnet/kan-bayashi_jsut_tts_train_vits_raw_phn_jaconv_pyopenjtalk_prosody_train.total_count.ave

Text-to-Speech • Updated Oct 23, 2021 • 1

espnet/kan-bayashi_vctk_full_band_multi_spk_vits

Text-to-Speech • Updated Oct 23, 2021 • 2 • 2

espnet/kan-bayashi_vctk_tts_train_full_band_multi_spk_vits_raw_phn_tacotron_g-truncated-50b003

Text-to-Speech • Updated Oct 23, 2021 • 2 • 1

espnet/kan-bayashi_vctk_multi_spk_vits

Text-to-Speech • Updated Oct 23, 2021 • 22

espnet/kan-bayashi_vctk_tts_train_multi_spk_vits_raw_phn_tacotron_g2p_en_no_space_train.total_count.ave

Text-to-Speech • Updated Oct 23, 2021