espnet AI Models

Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗

Tracked models
590
Downloads 30D
44.8K
Total downloads
1.5M
Total likes
654
Gained 7D
10.9K

Most downloaded

  1. 1owsm_ctc_v4_1BSep 20, 202611.1K
  2. 2fastspeech2_conformerOct 6, 20236,197
  3. 3fastspeech2_conformer_with_hifiganOct 5, 20235,820
  4. 4hubert_dummySep 18, 20264,773
  5. 5voxcelebs12_ecapa_wavlm_jointSep 18, 20264,205
  6. 6voxcelebs12_rawnet3Sep 18, 20263,909
  7. 7kamo-naoyuki-mini_an4_asr_train_raw_bpe_valid.acc.bestSep 19, 20261,741
  8. 8owsm_v4_small_370MSep 19, 2026230
  9. 9fastspeech2_conformer_hifiganSep 18, 2026214
  10. 10powsmJan 21, 2026193

Fastest growing

  1. 1owsm_ctc_v4_1B+3,217 in 7D11.1K
  2. 2hubert_dummy+2,082 in 7D4,773
  3. 3fastspeech2_conformer+1,739 in 7D6,197
  4. 4fastspeech2_conformer_with_hifigan+1,583 in 7D5,820
  5. 5voxcelebs12_rawnet3+1,281 in 7D3,909
  6. 6kamo-naoyuki-mini_an4_asr_train_raw_bpe_valid.acc.best+707 in 7D1,741
  7. 7kan-bayashi_ljspeech_vits+52 in 7D95
  8. 8xeus+17 in 7D90

Recently updated

  1. 1must_c_esp2_st_train_st_conformerSep 24, 20265
  2. 2must_c_st_train_st_conformerSep 24, 20269
  3. 3meld_esp2_cls_wavlm_base_plusSep 21, 202614
  4. 4multi-talker-whisper-small-amiSep 20, 202653
  5. 5anogkongda_librimix_enh_train_raw_valid.si_snr.aveSep 20, 202619
  6. 6dns_icassp21_enh_train_enh_tcn_tf_rawSep 20, 202612
  7. 7chenda-li-wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.aveSep 20, 202614
  8. 8anogkongda-librimix_enh_train_raw_valid.si_snr.aveSep 20, 202615
  9. 9Chenda_Li_wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.aveSep 20, 202617
  10. 10tedlium2_streaming_transformerSep 20, 202621

All models

All tracked models published by espnet
ModelDL 30D7D
myst_ogi_cmu_kids_aedespnet/myst_ogi_cmu_kids_aed5—
Karthik_DSTC2_asr_train_asr_wav2vec_transformerespnet/karthik_dstc2_asr_train_asr_wav2vec_transformer5—
jiyang_tang_aphsiabank_english_asr_ebranchformer_small_wavlm_large1espnet/jiyang_tang_aphsiabank_english_asr_ebranchformer_small_wavlm_large15—
OpenBEATS-Large-i1-enabirdsespnet/openbeats-large-i1-enabirds5—
arabic_commonvoice_blstmespnet/arabic_commonvoice_blstm5—
OpenBEATS-Large-i3-enabirdsespnet/openbeats-large-i3-enabirds5—
german_commonvoice_blstmespnet/german_commonvoice_blstm5—
OpenBEATS-Large-i2-hiceasespnet/openbeats-large-i2-hiceas5—
kan-bayashi_jsut_tacotron2_accent_with_pauseespnet/kan-bayashi_jsut_tacotron2_accent_with_pause5—
myst_ogi_cmu_kids_xeus_aedespnet/myst_ogi_cmu_kids_xeus_aed5—
kyrgyz_commonvoice_blstmespnet/kyrgyz_commonvoice_blstm5—
brianyan918_iwslt22_dialect_train_st_conformer_ctc0.3_lr2e-3_warmup15k_newspecaugespnet/brianyan918_iwslt22_dialect_train_st_conformer_ctc0.3_lr2e-3_warmup15k_newspecaug5—
BSCodecespnet/bscodec5—
GunnarThor_talromur_f_tacotron2espnet/gunnarthor_talromur_f_tacotron25—
kan-bayashi_jsut_fastspeechespnet/kan-bayashi_jsut_fastspeech5—
kiritan_svs_rnnespnet/kiritan_svs_rnn5—
Karthik_DSTC2_asr_train_asr_wav2vec_conformer_2espnet/karthik_dstc2_asr_train_asr_wav2vec_conformer_25—
asr_mlsuperb2_xeus_finetune_baselineespnet/asr_mlsuperb2_xeus_finetune_baseline5—
kan-bayashi_vctk_gst_transformerespnet/kan-bayashi_vctk_gst_transformer5—
simpleoier_librispeech_hubert_iter0_train_ssl_torchaudiohubert_base_960h_pretrain_it0_rawespnet/simpleoier_librispeech_hubert_iter0_train_ssl_torchaudiohubert_base_960h_pretrain_it0_raw5—
OpenBEATS-Base-i1-fsd50kespnet/openbeats-base-i1-fsd50k5—
m4singer_svs_xiaoiceespnet/m4singer_svs_xiaoice5—
kamo-naoyuki_librispeech_asr_train_asr_conformer5_raw_bpe5000_frontend-truncated-55c091espnet/kamo-naoyuki_librispeech_asr_train_asr_conformer5_raw_bpe5000_frontend-truncated-55c0915—
mls-multi_encodec_16kespnet/mls-multi_encodec_16k4—
kiritan_svs_xiaoiceespnet/kiritan_svs_xiaoice4—