Speech SSL models extended with sampling frequency independent convolution
Wataru-Nakata
Wataru
AI & ML interests
None yet
Recent Activity
updated a Space 18 days ago
sarulab-speech/sidon_demo_beta upvoted a paper about 1 month ago
Sidon: Fast and Robust Open-Source Multilingual Speech Restoration for
Large-scale Dataset Cleansing updated a Space about 2 months ago
Wataru/dsidonsamplesOrganizations
models 9
Wataru/sfi_w2v2_distill_ears
Feature Extraction • 94.7M • Updated • 55
Wataru/sfi_w2v2_encoder_copy
Feature Extraction • 94.7M • Updated • 1
Wataru/sfi_wavlm_distill_ears
Feature Extraction • 94.7M • Updated
Wataru/sfi_w2v2_distill_ears_2
Updated
Wataru/sfi_hubert_distill_ears
Feature Extraction • 94.7M • Updated
Wataru/sfi_hubert
Feature Extraction • 94.7M • Updated • 10 • 1
Wataru/ssl-vocoder
Updated • 2
Wataru/sentence-roberta-tiny
Feature Extraction • Updated • 4
Wataru/T5-base-ja-open2ch-dialogue
Updated • 4
datasets 0
None public yet