Model reference · open weights
fish-speech-1.2-sft is an open-weight audio or speech model from fishaudio. fish-speech-1.2-sft (BF16) weighs 981 MB; the smallest configuration that runs it is RTX 3060 12 GB.
Summary of the fishaudio/fish-speech-1.2-sft model card, 2026-10-01
What it is
| Released by | fishaudio |
|---|---|
| Released | 2024-07-18 |
| VRAM | 981 MB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
Fish Speech V1.2 is a leading text-to-speech (TTS) model trained on 300k hours of English, Chinese, and Japanese audio data.
Please refer to Fish Speech Github for more info. Demo available at Fish Audio.
If you found this repository useful, please consider citing this work:
@misc{fish-speech-v1,
author = {Shijia Liao, Tianyu Li},
title = {Fish Speech V1},
year = {2024},
publisher = {GitHub},
journal = {GitHub repository},
howpublished = {\url{https://github.com/fishaudio/fish-speech}}
}
This model is permissively licensed under the BY-CC-NC-SA-4.0 license. The source code is released under BY-CC-NC-SA-4.0 license.
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
How it works