TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: Local GLaDOS

8 点作者 dnhkng大约 1 年前
Code is available at: <a href="https:&#x2F;&#x2F;github.com&#x2F;dnhkng&#x2F;GlaDOS">https:&#x2F;&#x2F;github.com&#x2F;dnhkng&#x2F;GlaDOS</a><p>You can also run the Llama-3 8B GGUF, with the LLM, VAD, ASR and TTS models fitting on about 5 Gb of VRAM total, but it&#x27;s not as good at following the conversation and being interesting.<p>The goals for the project are:<p>All local! No OpenAI or ElevenLabs, this should be fully open source.<p>Minimal latency - You should get a voice response within 500 ms (but no canned responses!)<p>Interruptible - You should be able to interrupt whenever you want, but GLaDOS also has the right to be annoyed if you do...<p>Interactive - GLaDOS should have multi-modality, and be able to proactively initiate conversations (not yet done, but in planning)<p>Lastly, the code base should be small and simple (no PyTorch etc), with minimal layers of abstraction.

暂无评论

暂无评论