Fish-Audio-S2-Pro-NVFP4-Balanced

ajh-code/Fish-Audio-S2-Pro-NVFP4-Balanced

Text to Speech3.9B parametersfish-speechLicense: other

Tracked by OpenModelStats since September 6, 2026View on Hugging Face ↗

Downloads 30D: 124
Total downloads: 124
Gained 7D: +104(increase)
Gained 30D: —
Likes: 1; +1 in 7D
Rank · tracked models: —; –this week
Parameters: 3.9B
Last source update: Aug 27, 2026

Fish-Audio-S2-Pro-NVFP4-Balanced gained 104 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 2026-09-06. Charts appear as daily observations accumulate.

Overview

Fish-Audio-S2-Pro-NVFP4-Balanced is a text to speech model published by ajh-code. OpenModelStats has tracked the model since Sep 6, 2026, most recently observing it Sep 24, 2026.

Published: Aug 27, 2026
Last updated: Aug 27, 2026
Library: fish-speech
License: other
Task: Text to Speech
Parameters: 3,924,842,496
Spaces: —
Derivative models: —
Velocity 7D/day: 15

fish-speechsafetensorsfish_qwen3_omnifish-audiotext-to-speechvoice-cloningquantizationnvfp4mxfp8blackwellsm120english

Publisher

ajh-codeView publisher statistics →

Derived from fishaudio/s2-pro (reported by the source; parent not yet tracked).

Similar models

Models similar to Fish-Audio-S2-Pro-NVFP4-Balanced
Model	Task	DL 30D	Likes	Params
Voxtral-4B-TTS-2603-mlx-6bitmlx-community	Text to Speech	792	5	4B
Llasa-3BHKUSTAudio	Text to Speech	331	531	4B
LongCat-AudioDiT-3.5B-bf16drbaph	Text to Speech	5,680	6	3.8B
Veenamaya-research	Text to Speech	4,032	240	3.8B
orpheus-3b-0.1-ftcanopylabs	Text to Speech	30.7K	745	3.8B
orpheus-3b-0.1-ftjetjodh	Text to Speech	5,314	0	3.8B