Yifan Peng

pyf98's activity

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

authored 5 papers 4 days ago

ESPnet-SLU: Advancing Spoken Language Understanding through ESPnet

Paper • 2111.14706 • Published Nov 29, 2021

On the Effects of Heterogeneous Data Sources on Speech-to-Text Foundation Models

Paper • 2406.09282 • Published Jun 13, 2024

OWLS: Scaling Laws for Multilingual Speech Recognition and Translation Models

Paper • 2502.10373 • Published Feb 14

Granary: Speech Recognition and Translation Dataset in 25 European Languages

Paper • 2505.13404 • Published 18 days ago

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning

Paper • 2506.00338 • Published 7 days ago • 8

updated a collection 4 days ago

Open Whisper-style Speech Models (OWSM)

Collection

Fully open Whisper-style speech foundation models developed by CMU WAVLab: https://www.wavlab.org/activities/2024/owsm/ • 21 items • Updated 4 days ago • 5

commented a paper 4 days ago

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning

Paper • 2506.00338 • Published 7 days ago • 8 •

2

upvoted a paper 4 days ago

OWSM v4: Improving Open Whisper-Style Speech Models via Data Scaling and Cleaning

Paper • 2506.00338 • Published 7 days ago • 8

updated a dataset 4 days ago

espnet/yodas_owsmv4

Updated 3 days ago • 85 • 3

updated 4 models 4 days ago

espnet/owsm_ctc_v4_1B

Automatic Speech Recognition • Updated 4 days ago • 52 • 2

espnet/owsm_v4_base_102M

Automatic Speech Recognition • Updated 3 days ago • 20 • 1

espnet/owsm_v4_small_370M

Automatic Speech Recognition • Updated 4 days ago • 23 • 1

espnet/owsm_v4_medium_1B

Automatic Speech Recognition • Updated 3 days ago • 41 • 1

New activity in espnet/owsm_v4_medium_1B 4 days ago

where can i find the v4 paper

2

#1 opened 4 days ago by

StephennFernandes

liked a dataset 4 days ago

espnet/yodas_owsmv4

Updated 3 days ago • 85 • 3

updated a collection 4 days ago

Open Whisper-style Speech Models (OWSM)

Collection

Fully open Whisper-style speech foundation models developed by CMU WAVLab: https://www.wavlab.org/activities/2024/owsm/ • 21 items • Updated 4 days ago • 5

published a dataset 4 days ago

espnet/yodas_owsmv4

Updated 3 days ago • 85 • 3

liked 3 models 18 days ago

espnet/owsm_ctc_v4_1B

Automatic Speech Recognition • Updated 4 days ago • 52 • 2

espnet/owsm_v4_base_102M

Automatic Speech Recognition • Updated 3 days ago • 20 • 1

espnet/owsm_v4_small_370M

Automatic Speech Recognition • Updated 4 days ago • 23 • 1