bf16 Open on Hugging Face
Parameters
4.6B
Weights (est.)
≈ 9.1 GB
Mac memory (est.)
16 GB+
Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.
Details
- Base model
- fishaudio/s2-pro (finetune)
- Vendor
- fishaudio
- Task
- Text to speech
- Quantisation
- bf16
- Licence
- fish-audio-research
- Downloads
- 1.4K in the last 30 days · 11K all time · 29 likes
- Published
- 2026-03-11 · updated 2026-03-20 (7mo ago)
- Languages
- en, zh, ja, ko, es, pt, ar, ru, fr, de, sv, it, tr, no, nl, cy, eu, ca, da, gl, ta, hu, fi, pl, et, hi, la, ur, th, vi, jv, bn, yo, cs, sw, he, ms, uk, id, kk
- Tags
- mlx-audio, fish_qwen3_omni, speech, speech generation, voice cloning
Other MLX builds of fishaudio/s2-pro
| Build | Quantisation | Weights | Mac memory | Downloads |
|---|---|---|---|---|
| fish-audio-s2-pro-8bit | 8-bit | ≈ 4.8 GB | 8 GB+ | 2.9K |
| fishaudio-s2-pro-8bit-mlx | 8-bit | ≈ 4.8 GB | 8 GB+ | 295 |
| fish-audio-s2-pro-bf16 (this one) | bf16 | ≈ 9.1 GB | 16 GB+ | 1.4K |