espnet AI Models
Tracked by OpenModelStats since Aug 23, 2026 · View on Hugging Face ↗
- Tracked modelsRepositories from this publisher currently tracked by OpenModelStats.
- 590
- Downloads 30DSum of each tracked model's rolling recent-downloads counter. A sum of repository counters is not a count of unique users.
- 44.8K
- Total downloadsSum of cumulative all-time download counters across tracked repositories.
- 1.5M
- Total likes
- 654
- Gained 7DCombined seven-day cumulative-download gains measured by OpenModelStats.
- 10.9K
Most downloaded
- 1owsm_ctc_v4_1BSep 20, 202611.1K
- 2fastspeech2_conformerOct 6, 20236,197
- 3fastspeech2_conformer_with_hifiganOct 5, 20235,820
- 4hubert_dummySep 18, 20264,773
- 5voxcelebs12_ecapa_wavlm_jointSep 18, 20264,205
- 6voxcelebs12_rawnet3Sep 18, 20263,909
- 7kamo-naoyuki-mini_an4_asr_train_raw_bpe_valid.acc.bestSep 19, 20261,741
- 8owsm_v4_small_370MSep 19, 2026230
- 9fastspeech2_conformer_hifiganSep 18, 2026214
- 10powsmJan 21, 2026193
Fastest growing
- 1owsm_ctc_v4_1B+3,217 in 7D11.1K
- 2hubert_dummy+2,082 in 7D4,773
- 3fastspeech2_conformer+1,739 in 7D6,197
- 4fastspeech2_conformer_with_hifigan+1,583 in 7D5,820
- 5voxcelebs12_rawnet3+1,281 in 7D3,909
- 6kamo-naoyuki-mini_an4_asr_train_raw_bpe_valid.acc.best+707 in 7D1,741
- 7kan-bayashi_ljspeech_vits+52 in 7D95
- 8xeus+17 in 7D90
Recently updated
- 1must_c_esp2_st_train_st_conformerSep 24, 20265
- 2must_c_st_train_st_conformerSep 24, 20269
- 3meld_esp2_cls_wavlm_base_plusSep 21, 202614
- 4multi-talker-whisper-small-amiSep 20, 202653
- 5anogkongda_librimix_enh_train_raw_valid.si_snr.aveSep 20, 202619
- 6dns_icassp21_enh_train_enh_tcn_tf_rawSep 20, 202612
- 7chenda-li-wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.aveSep 20, 202614
- 8anogkongda-librimix_enh_train_raw_valid.si_snr.aveSep 20, 202615
- 9Chenda_Li_wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.aveSep 20, 202617
- 10tedlium2_streaming_transformerSep 20, 202621
All models
| Model | DL 30D | 7D |
|---|---|---|
| aishell2_transducerespnet/aishell2_transducer | 8 | — |
| kan-bayashi_jsut_tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_train.loss.aveespnet/kan-bayashi_jsut_tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_train.loss.ave | 8 | — |
| interspeech2024_dsuchallenge_wavlm_large_21_baselineespnet/interspeech2024_dsuchallenge_wavlm_large_21_baseline | 8 | — |
| kan-bayashi_jsut_full_band_vits_prosodyespnet/kan-bayashi_jsut_full_band_vits_prosody | 8 | — |
| YushiUeda_iemocap_sentiment_asr_train_asr_conformer_hubertespnet/yushiueda_iemocap_sentiment_asr_train_asr_conformer_hubert | 8 | — |
| kan-bayashi_jsut_tts_train_conformer_fastspeech2_transformer_teacher_r-truncated-74c1b4espnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_transformer_teacher_r-truncated-74c1b4 | 8 | — |
| kan-bayashi_jsut_conformer_fastspeech2_accentespnet/kan-bayashi_jsut_conformer_fastspeech2_accent | 8 | — |
| belarusian_commonvoice_blstmespnet/belarusian_commonvoice_blstm | 8 | — |
| kan-bayashi_ljspeech_tts_train_fastspeech_raw_phn_tacotron_g2p_en_no_space_train.loss.bestespnet/kan-bayashi_ljspeech_tts_train_fastspeech_raw_phn_tacotron_g2p_en_no_space_train.loss.best | 8 | — |
| acesinger_opencpop_visinger2_44khzespnet/acesinger_opencpop_visinger2_44khz | 8 | — |
| asr_mlsuperb2_xlsr_finetune_baselineespnet/asr_mlsuperb2_xlsr_finetune_baseline | 8 | — |
| zuazo_commonvoice_asr_train_asr_conformer5_raw_eu_bpe150_spespnet/zuazo_commonvoice_asr_train_asr_conformer5_raw_eu_bpe150_sp | 8 | — |
| kan-bayashi_ljspeech_tts_train_joint_conformer_fastspeech2_hifigan_raw-truncated-af8fe0espnet/kan-bayashi_ljspeech_tts_train_joint_conformer_fastspeech2_hifigan_raw-truncated-af8fe0 | 8 | — |
| akreal_lh_small_asr2_e_branchformer_wavlm_mistral02_ctcespnet/akreal_lh_small_asr2_e_branchformer_wavlm_mistral02_ctc | 8 | — |
| interspeech2024_dsuchallenge_wavlm_large_21_km2000_bpe_rm3000_bpe_ts6500_baselineespnet/interspeech2024_dsuchallenge_wavlm_large_21_km2000_bpe_rm3000_bpe_ts6500_baseline | 8 | — |
| myst_wavlm_aed_transformerespnet/myst_wavlm_aed_transformer | 8 | — |
| kan-bayashi_jsut_conformer_fastspeech2_tacotron2_prosodyespnet/kan-bayashi_jsut_conformer_fastspeech2_tacotron2_prosody | 8 | — |
| ftshijt_mls_asr_transformer_valid.acc.bestespnet/ftshijt_mls_asr_transformer_valid.acc.best | 8 | — |
| roshansh_asr_base_sp_conformer_swbdespnet/roshansh_asr_base_sp_conformer_swbd | 8 | — |
| talromur2_xvector_tacotron2espnet/talromur2_xvector_tacotron2 | 8 | — |
| kan-bayashi_csmsc_tts_train_transformer_raw_phn_pypinyin_g2p_phone_train.loss.aveespnet/kan-bayashi_csmsc_tts_train_transformer_raw_phn_pypinyin_g2p_phone_train.loss.ave | 8 | — |
| siddhana_fsc_challenge_asr_train_asr_hubert_transformer_adam_specaug_r-truncated-36174despnet/siddhana_fsc_challenge_asr_train_asr_hubert_transformer_adam_specaug_r-truncated-36174d | 8 | — |
| YushiUeda_swbd_sentiment_asr_train_asr_conformer_wav2vec2espnet/yushiueda_swbd_sentiment_asr_train_asr_conformer_wav2vec2 | 8 | — |
| kan-bayashi_vctk_gst_tacotron2espnet/kan-bayashi_vctk_gst_tacotron2 | 8 | — |
| GunnarThor_talromur_e_fastspeech2espnet/gunnarthor_talromur_e_fastspeech2 | 8 | — |