Shinji Watanabe

sw005320's activity

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

updated a model about 15 hours ago

espnet/owsm_ctc_v4_1B

Automatic Speech Recognition • Updated about 15 hours ago • 11.1k • 14

updated 2 Spaces about 20 hours ago

Running on Zero

Agents

1

OWSM-CTC v4

🎙

1

151 languages in, 25 translation targets out, fast

Running on Zero

Agents

OWSM v4

🌍

151 languages in, 25 translation targets out, promptable

updated 5 models about 20 hours ago

espnet/owsm_v3.1_ebf_small

Automatic Speech Recognition • Updated about 20 hours ago • 29 • 2

espnet/owsm_v3.1_ebf_base

Automatic Speech Recognition • Updated about 20 hours ago • 55 • 3

espnet/owsm_v3.1_ebf

Automatic Speech Recognition • Updated about 20 hours ago • 108 • 17

espnet/owsm_v3.1_ebf_small_lowrestriction

Automatic Speech Recognition • Updated about 20 hours ago • 26 • 3

espnet/owsm_v3

Automatic Speech Recognition • Updated about 20 hours ago • 31 • 29

updated 3 models about 21 hours ago

espnet/owsm_v4_small_370M

Automatic Speech Recognition • Updated about 21 hours ago • 237 • 4

espnet/owsm_v4_base_102M

Automatic Speech Recognition • Updated about 21 hours ago • 140 • 1

espnet/owsm_v4_medium_1B

Automatic Speech Recognition • Updated about 21 hours ago • 103 • 6

updated a Space about 22 hours ago

Running on Zero

Agents

11

OWSM v4

🌍

11

The same demo as espnet/owsm-v4, kept at this older address

upvoted an article 13 days ago

view article

Article

YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research

• 

espnet

•

14 days ago

• 36

liked a dataset 14 days ago

espnet/yodas3

Viewer • Updated 4 days ago • 4.08M • 225k • 232

updated a Space 14 days ago

Running on Zero

Agents

1

POWSM-CTC

🐁

1

What you said in phones, IPA, from a phonetic model

published an article 14 days ago

view article

Article

YODAS v3: A 1 Million Hour Dataset for the Next Generation of Open Voice AI Research

• 

espnet

•

14 days ago

• 36

updated a Space 18 days ago

Running on Zero

Agents

Forced alignment

📐

When each line was said, and how sure the model is

published 2 Spaces 18 days ago

Running on Zero

Agents

Forced alignment

📐

When each line was said, and how sure the model is

Running on Zero

Agents

1

POWSM-CTC

🐁

1

What you said in phones, IPA, from a phonetic model

updated a model 21 days ago

espnet/dns_icassp21_enh_train_enh_tcn_tf_raw

Audio-to-Audio • Updated 21 days ago • 22