drbaph/dots.tts-soar-bf16

认证创作者 drbaph 已认证
🤗 Hugging Face 来源text-to-speechapache-2.04.4 GBother✓ 1 个校验和今天更新
一条命令提交

在你的模型文件夹旁边运行它。它会制作种子、将文件与 Hugging Face 比对,然后提交。你只需开始做种,并粘贴你账户中的密钥。它只读取你的文件,绝不修改。如果愿意,可以先阅读脚本。

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo drbaph/dots.tts-soar-bf16 ./model-folder
需要做种者 →

dots.tts-soar-bf16

BF16-converted version of rednote-hilab/dots.tts-soar for use with Dots-TTS-ComfyUI.

This checkpoint reduces disk usage and VRAM requirements while maintaining output quality comparable to the original FP32 release.

Requirements

Installation

ComfyUI/
└── models/
    └── dotstts/
        ├── common/
        │   ├── speaker_encoder.safetensors
        │   └── vocoder.safetensors
        └── dots.tts-soar-bf16/
            └── dots.tts-soar-bf16.safetensors

Notes

  • Converted from the original FP32 checkpoint.
  • Lower storage requirements.
  • Reduced VRAM usage.
  • Compatible with Dots-TTS-ComfyUI.

License

Apache-2.0