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, 202611.2K
- 2fastspeech2_conformerOct 6, 20236,276
- 3fastspeech2_conformer_with_hifiganOct 5, 20235,878
- 4hubert_dummySep 18, 20264,869
- 5voxcelebs12_rawnet3Sep 18, 20264,302
- 6voxcelebs12_ecapa_wavlm_jointSep 18, 20264,182
- 7kamo-naoyuki-mini_an4_asr_train_raw_bpe_valid.acc.bestSep 19, 20261,752
- 8owsm_v4_small_370MSep 19, 2026226
- 9fastspeech2_conformer_hifiganSep 18, 2026214
- 10powsmJan 21, 2026203
Fastest growing
- 1owsm_ctc_v4_1B+3,217 in 7D11.2K
- 2hubert_dummy+2,082 in 7D4,869
- 3fastspeech2_conformer+1,739 in 7D6,276
- 4fastspeech2_conformer_with_hifigan+1,583 in 7D5,878
- 5voxcelebs12_rawnet3+1,281 in 7D4,302
- 6kamo-naoyuki-mini_an4_asr_train_raw_bpe_valid.acc.best+707 in 7D1,752
- 7kan-bayashi_ljspeech_vits+52 in 7D95
- 8xeus+17 in 7D89
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 |
|---|---|---|
| voxcelebs12_ecapa_frozenespnet/voxcelebs12_ecapa_frozen | 12 | — |
| kan-bayashi_jsut_tts_train_fastspeech2_raw_phn_jaconv_pyopenjtalk_train.loss.aveespnet/kan-bayashi_jsut_tts_train_fastspeech2_raw_phn_jaconv_pyopenjtalk_train.loss.ave | 12 | — |
| siddhana_fsc_unseen_asr_train_asr_hubert_transformer_adam_specaug_fine-truncated-ef9dabespnet/siddhana_fsc_unseen_asr_train_asr_hubert_transformer_adam_specaug_fine-truncated-ef9dab | 12 | — |
| kan-bayashi_vctk_tts_train_xvector_conformer_fastspeech2_transformer_t-truncated-69a657espnet/kan-bayashi_vctk_tts_train_xvector_conformer_fastspeech2_transformer_t-truncated-69a657 | 12 | — |
| kan-bayashi_vctk_tts_train_gst_xvector_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.aveespnet/kan-bayashi_vctk_tts_train_gst_xvector_tacotron2_raw_phn_tacotron_g2p_en_no_space_train.loss.ave | 12 | — |
| voxcelebs12devs_voxblinkclean_rawnet3espnet/voxcelebs12devs_voxblinkclean_rawnet3 | 12 | — |
| kamo-naoyuki_chime4_asr_train_asr_transformer3_raw_en_char_sp_valid.acc.aveespnet/kamo-naoyuki_chime4_asr_train_asr_transformer3_raw_en_char_sp_valid.acc.ave | 11 | — |
| kan-bayashi_jvs_jvs010_vits_accent_with_pauseespnet/kan-bayashi_jvs_jvs010_vits_accent_with_pause | 11 | — |
| juice500ml_mls_10h_asr_fbankespnet/juice500ml_mls_10h_asr_fbank | 11 | — |
| ftshijt_espnet2_asr_yolo_mixtec_transformerespnet/ftshijt_espnet2_asr_yolo_mixtec_transformer | 11 | — |
| kan-bayashi_jsut_fastspeech2espnet/kan-bayashi_jsut_fastspeech2 | 11 | — |
| espnet_tts_vctk_espnet_spk_voxceleb12_rawnetespnet/espnet_tts_vctk_espnet_spk_voxceleb12_rawnet | 11 | — |
| kan-bayashi_libritts_tts_train_gst_xvector_trasnformer_raw_phn_tacotro-truncated-250027espnet/kan-bayashi_libritts_tts_train_gst_xvector_trasnformer_raw_phn_tacotro-truncated-250027 | 11 | — |
| kan-bayashi_csmsc_tacotron2espnet/kan-bayashi_csmsc_tacotron2 | 11 | — |
| americasnlp22-asr-quyespnet/americasnlp22-asr-quy | 11 | — |
| akreal_swbd_da_hubert_conformerespnet/akreal_swbd_da_hubert_conformer | 11 | — |
| kan_bayashi_jsut_tts_train_conformer_fastspeech2_raw_phn_jaconv_pyopenjtalk_train.loss.aveespnet/kan_bayashi_jsut_tts_train_conformer_fastspeech2_raw_phn_jaconv_pyopenjtalk_train.loss.ave | 11 | — |
| kan-bayashi_vctk_multi_spk_vitsespnet/kan-bayashi_vctk_multi_spk_vits | 11 | — |
| kan-bayashi_jsut_tts_train_conformer_fastspeech2_transformer_teacher_r-truncated-f43d8fespnet/kan-bayashi_jsut_tts_train_conformer_fastspeech2_transformer_teacher_r-truncated-f43d8f | 11 | — |
| OpenBEATS-Base-i2-as20kespnet/openbeats-base-i2-as20k | 11 | — |
| marathi_openslr64espnet/marathi_openslr64 | 11 | — |
| kan-bayashi_jsut_tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause_train.loss.aveespnet/kan-bayashi_jsut_tts_train_tacotron2_raw_phn_jaconv_pyopenjtalk_accent_with_pause_train.loss.ave | 11 | — |
| kan-bayashi_csmsc_transformerespnet/kan-bayashi_csmsc_transformer | 11 | — |
| siddhana_slue_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10bestespnet/siddhana_slue_asr_train_asr_conformer_raw_en_word_valid.acc.ave_10best | 11 | — |
| Yushi_Ueda_ksponspeech_asr_train_asr_conformer8_n_fft512_hop_length256-truncated-eb42e5espnet/yushi_ueda_ksponspeech_asr_train_asr_conformer8_n_fft512_hop_length256-truncated-eb42e5 | 11 | — |