Xuankai Chang

simpleoier's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 14 days ago

One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation

Paper • 2512.07829 • Published 16 days ago • 21

authored a paper over 1 year ago

Towards Robust Speech Representation Learning for Thousands of Languages

Paper • 2407.00837 • Published Jun 30, 2024 • 11

updated a dataset almost 2 years ago

discrete-speech/interspeech2024_discrete_speech_asr_results

Viewer • Updated Mar 17, 2024 • 13 • 120

updated a Space almost 2 years ago

Running

Leaderboard for ASR track

🥇

Explore and filter speech model evaluations

updated a model almost 2 years ago

espnet/interspeech2024_dsuchallenge_wavlm_large_21_km2000_bpe_rm3000_bpe_ts6500_baseline

Automatic Speech Recognition • Updated Feb 29, 2024 • 4

updated a dataset almost 2 years ago

discrete-speech/interspeech2024_discrete_speech_asr_requests

Updated Feb 27, 2024 • 5

authored a paper almost 2 years ago

OWSM v3.1: Better and Faster Open Whisper-Style Speech Models based on E-Branchformer

Paper • 2401.16658 • Published Jan 30, 2024 • 14

updated a model almost 2 years ago

espnet/interspeech2024_dsuchallenge_wavlm_large_21_baseline

Automatic Speech Recognition • Updated Jan 20, 2024 • 3

authored a paper about 2 years ago

UniAudio: An Audio Foundation Model Toward Universal Audio Generation

Paper • 2310.00704 • Published Oct 1, 2023 • 21

updated 6 models over 2 years ago

simpleoier/simpleoier_covost2_discrete_asr_e_branchformer1_km1000_raw_es_mhubert_km1k_bpe_rm5k_bpe_ts1k_sp

Updated Jul 15, 2023

espnet/simpleoier_librispeech_hubert_iter1_train_ssl_torchaudiohubert_base_960h_pretrain_it1_raw

Updated Jul 6, 2023 • 7

espnet/simpleoier_librispeech_hubert_iter0_train_ssl_torchaudiohubert_base_960h_pretrain_it0_raw

Updated Jul 6, 2023 • 3

espnet/simpleoier_ls960_asr2_e_branchformer1_conv1d3_1gpu_raw_wavlm_large_21_km1k_bpe_rm5k_bpe_ts5k_sp

Automatic Speech Recognition • Updated Jun 23, 2023 • 2

espnet/simpleoier_ls960_asr2_train_e_branchformer1_1gpu_raw_wavlm_large_21_km1k_bpe_rm5k_bpe_ts5k_sp

Automatic Speech Recognition • Updated Jun 23, 2023 • 2

espnet/simpleoier_ls960_asr2_train_e_branchformer1_raw_wavlm_large_21_km2000_bpe_rm6000_bpe_ts5000_sp

Automatic Speech Recognition • Updated Jun 22, 2023 • 3

New activity in espnet/simpleoier_librispeech_asr_train_asr_conformer7_wavlm_large_raw_en_bpe5000_sp over 2 years ago

Filepath seems to be hardcoded?

2

#1 opened over 2 years ago by

kalbin

updated a model over 2 years ago

espnet/simpleoier_librispeech_asr_train_asr_conformer7_wavlm_large_raw_en_bpe5000_sp

Automatic Speech Recognition • Updated May 8, 2023 • 18 • 1

updated a model almost 3 years ago

espnet/simpleoier_librilight_limited_asr_train_asr_hubert_base_10h_finetuning_raw_en_char

Automatic Speech Recognition • Updated Jan 11, 2023 • 5

updated a model about 3 years ago

espnet/simpleoier_librimix_asr_train_asr_transformer_multispkr_raw_en_char_sp

Automatic Speech Recognition • Updated Nov 23, 2022 • 4

updated a model over 3 years ago

espnet/simpleoier_chime6_asr_transformer_wavlm_lr1e-3

Automatic Speech Recognition • Updated May 3, 2022 • 2