wavlm-base-plus-hiragana-ctc

TylorShine/wavlm-base-plus-hiragana-ctc

Speech Recognition94.5M parameterstransformersLicense: cc-by-sa-3.0

Tracked by OpenModelStats since September 13, 2026View on Hugging Face ↗

Downloads 30D: 84
Total downloads: 439
Gained 7D: +39(increase)
Gained 30D: —
Likes: 1; +0 in 7D
Rank · tracked models: —; –this week
Parameters: 94.5M
Last source update: Mar 6, 2026

wavlm-base-plus-hiragana-ctc gained 39 downloads during the last seven tracked days.

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-13. Charts appear as daily observations accumulate.

Overview

wavlm-base-plus-hiragana-ctc is a speech recognition model published by TylorShine. OpenModelStats has tracked the model since Sep 13, 2026, most recently observing it 35h ago.

Published: Mar 5, 2026
Last updated: Mar 6, 2026
Library: transformers
License: cc-by-sa-3.0
Task: Speech Recognition
Parameters: 94,480,368
Spaces: —
Derivative models: —
Velocity 7D/day: 6

transformerssafetensorsdual_ctcfeature-extractionautomatic-speech-recognitionctcwavlmjapanesehiraganaphonemecustom_codeja

Publisher

TylorShineView publisher statistics →

Model family

Based on base-model relationships reported by the source's metadata.

Base model

wavlm-base-plus303K

Sibling models

Similar models

Models similar to wavlm-base-plus-hiragana-ctc
Model	Task	DL 30D	Likes	Params
wav2vec2-base-japanese-asrTKU410410103	Speech Recognition	498	4	94.5M
wav2vec2-base-en-phoneme-ctc-41hbobboyms	Speech Recognition	304	0	94.5M
wav2vec2-base-vietnamesedragonSwing	Speech Recognition	4,198	2	94.4M
Wolof-HuBERT-CTCsoynade-research	Speech Recognition	394	2	94.4M
swecha-gonthuka-asrswechatelangana	Speech Recognition	379	8	94.4M
wav2vec2-vedic-alignerchiranjeevisagi	Speech Recognition	1,039	0	94.4M