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

cjli authored a paper 6 days ago

Prompt-MII: Meta-Learning Instruction Induction for LLMs

cjli authored a paper 6 days ago

POWSM: A Phonetic Open Whisper-Style Speech Foundation Model

cjli authored a paper 6 days ago

Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention

View all activity

espnet 's models 653

espnet/kan-bayashi_jsut_tts_train_fastspeech2_tacotron2_teacher_raw_phn_jacon-truncated-f45dcb

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_jsut_tts_train_transformer_raw_phn_jaconv_pyopenjtalk_accent_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_jsut_tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021 • 1

espnet/Hoon_Chung_jsut_asr_train_asr_conformer8_raw_char_sp_valid.acc.ave

Automatic Speech Recognition • Updated Jul 3, 2021 • 4 • 1

espnet/kamo-naoyuki_timit_asr_train_asr_raw_word_valid.acc.ave

Automatic Speech Recognition • Updated Jul 3, 2021

espnet/kamo-naoyuki_reverb_asr_train_asr_transformer4_raw_char_batch_bins1600-truncated-1b72bb

Automatic Speech Recognition • Updated Jul 3, 2021

espnet/kamo-naoyuki_wsj_transformer2

Automatic Speech Recognition • Updated Jul 3, 2021

espnet/kamo-naoyuki_aishell_conformer

Automatic Speech Recognition • Updated Jul 3, 2021 • 1

espnet/kan-bayashi_ljspeech_transformer

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_ljspeech_tts_train_transformer_raw_phn_tacotron_g2p_en_no_space_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_csj_asr_train_asr_transformer_raw_char_sp_valid.acc.ave

Automatic Speech Recognition • Updated Jul 3, 2021 • 3

espnet/kan-bayashi_vctk_gst_conformer_fastspeech2

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_vctk_gst_fastspeech2

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_vctk_gst_transformer

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_csmsc_transformer

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_jsut_transformer

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_ljspeech_conformer_fastspeech2

Text-to-Speech • Updated Jul 3, 2021 • 2 • 1

espnet/kan-bayashi_ljspeech_fastspeech2

Text-to-Speech • Updated Jul 3, 2021 • 2

espnet/kan-bayashi_vctk_tts_train_gst_conformer_fastspeech2_raw_phn_tacotron_-truncated-69081b

Text-to-Speech • Updated Jul 3, 2021 • 1

espnet/kan-bayashi_vctk_tts_train_gst_fastspeech2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_vctk_tts_train_gst_transformer_raw_phn_tacotron_g2p_en_no_space_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_csmsc_tts_train_transformer_raw_phn_pypinyin_g2p_phone_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021 • 1

espnet/kan-bayashi_jsut_tts_train_transformer_raw_phn_jaconv_pyopenjtalk_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_ljspeech_tts_train_conformer_fastspeech2_raw_phn_tacotron_-truncated-ec9e34

Text-to-Speech • Updated Jul 3, 2021 • 1

espnet/kan-bayashi_ljspeech_tts_train_fastspeech2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021 • 1 • 1

espnet/kan-bayashi_csmsc_fastspeech2

Text-to-Speech • Updated Jul 3, 2021 • 2 • 2

espnet/kan-bayashi_jsut_conformer_fastspeech2

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_jsut_fastspeech2

Text-to-Speech • Updated Jul 3, 2021 • 4

espnet/kan-bayashi_csmsc_tts_train_conformer_fastspeech2_raw_phn_pypinyin_g2p_phone_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021

espnet/kan-bayashi_csmsc_tts_train_fastspeech2_raw_phn_pypinyin_g2p_phone_train.loss.ave

Text-to-Speech • Updated Jul 3, 2021 • 2