Llasa-1B

HKUSTAudio/Llasa-1B

Text to Speech1.4B parametersLicense: cc-by-nc-4.0
Tracked by OpenModelStats since September 3, 2026View on Hugging Face ↗
Downloads 30D
1,001
Total downloads
155.3K
Gained 7D
+246(increase)
0.2%(up) vs baseline
Gained 30D
—
Likes
104
+0 in 7D
Rank · tracked models
#32,757
1282(down 1282 places)this week
Parameters
1.4B
Last source update
May 10, 2025
Momentum
36.7
  • Llasa-1B gained 246 downloads during the last seven tracked days.
  • It moved from #347 to #367 among tracked Text to Speech models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Llasa-1B is a text to speech model published by HKUSTAudio. OpenModelStats has tracked the model since Sep 3, 2026, most recently observing it Oct 3, 2026.

Published
Jan 7, 2025
Last updated
May 10, 2025
Library
—
License
cc-by-nc-4.0
Task
Text to Speech
Parameters
1,370,048,512
Spaces
—
Derivative models
—
Velocity 7D/day
35
safetensorsllamaText-to-Speechtext-to-speechzhenarxiv:2502.04128base_model:meta-llama/Llama-3.2-1B-Instructbase_model:finetune:meta-llama/Llama-3.2-1B-Instructlicense:cc-by-nc-4.0region:us

Publisher

HKUSTAudioView publisher statistics →

Derived from meta-llama/Llama-3.2-1B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to Llasa-1B
ModelDL 30D
vibevoice-realtime-0.5b-with-encodermohammed-bahumaish554
Llama-OuteTTS-1.0-1Bunsloth5,588
Llama-OuteTTS-1.0-1BOuteAI2,600
csm-1bsesame136.6K
OuteTTS-0.3-1BOuteAI140
Dia-1.6Bnari-labs27.8K
HKUSTAudio/Llasa-1B — Downloads, Growth & Stats | OpenModelStats