English注册

audio-cpp/VibeVoice-7B-GGUF

🤗 Hugging Face 来源text-to-speechmit激活 7B11 GBGGUF✓ 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 audio-cpp/VibeVoice-7B-GGUF ./model-folder
需要做种者 →

VibeVoice 7B GGUF for audio.cpp

GGUF conversion of vibevoice/VibeVoice-7B for audio.cpp.

Upstream model: vibevoice/VibeVoice-7B

Files

  • vibevoice-7b-q8_0.gguf: Q8_0 GGUF package for VibeVoice 7B.
  • LICENSE: MIT license from the upstream VibeVoice project.

Usage

Use the GGUF directly with audio.cpp CLI/server, or download/select it from the native WebUI once the package is published.

VibeVoice is a long-form, multi-speaker speech generation model. It is intended for English and Chinese speech synthesis.

Local audio.cpp check

Observed quick-check performance on RTX 5090 for the Q8_0 GGUF in audio.cpp server mode:

  • RTF: about 0.18
  • Output length: about 52s
  • Peak VRAM: about 13.3 GB

These numbers are implementation and hardware dependent. They are only a quick audio.cpp sanity check, not a benchmark.