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。

OpenVINO AI effects for Audacity

151 点作者 wazoox3 个月前

5 条评论

mmastrac3 个月前
I tried the Audacity noise-removal plugin recently and it&#x27;s complete crap. I fed a high-quality audio stream from a Rode mic into a few different options to see which could remove the noise of my server rack. iMovie made the voice sound like a robot and Audacity barely did anything. The only thing that worked was DeepFilterNet and it&#x27;s free, open-source and cargo installable.<p>There&#x27;s no reason to lock yourself into an intel-only solution. Just use DeepFilterNet. The results of this on my noisy server room were insanely good. Almost no voice dropout with 100% fan noise removal.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;Rikorose&#x2F;DeepFilterNet">https:&#x2F;&#x2F;github.com&#x2F;Rikorose&#x2F;DeepFilterNet</a><p>EDIT: Even more interesting, it looks like OpenVino is just DeepFilterNet glued to Whisper.cpp and tied to Intel hardware.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;intel&#x2F;openvino-plugins-ai-audacity&#x2F;tree&#x2F;main&#x2F;mod-openvino&#x2F;noise_suppression&#x2F;deepfilternet">https:&#x2F;&#x2F;github.com&#x2F;intel&#x2F;openvino-plugins-ai-audacity&#x2F;tree&#x2F;m...</a>
评论 #43069541 未加载
评论 #43071356 未加载
评论 #43073763 未加载
sorenjan3 个月前
This only works with Intel GPUs, and CPUs and NPUs. No Nvidia support for instance.<p><a href="https:&#x2F;&#x2F;docs.openvino.ai&#x2F;2024&#x2F;about-openvino&#x2F;release-notes-openvino&#x2F;system-requirements.html#gpu" rel="nofollow">https:&#x2F;&#x2F;docs.openvino.ai&#x2F;2024&#x2F;about-openvino&#x2F;release-notes-o...</a>
评论 #43071254 未加载
评论 #43076931 未加载
评论 #43069699 未加载
评论 #43093861 未加载
评论 #43068900 未加载
评论 #43070404 未加载
smusamashah3 个月前
Is there a tool that can remove very noisy audio recording of a song using actual song as a reference?<p>I found a very old audio cassette from my childhood with me and some other kids talking while a song is playing in background. I tried subtracting the song using Audacity but for that to work reference song and recording must align &quot;perfectly&quot; which is very very hard. Not just the timing (which i found can be a problem with cassettes) loudness&#x2F;frequency distribution must also align perfectly.<p>Found Smartsubtract <a href="https:&#x2F;&#x2F;oxfordwaveresearch.com&#x2F;products&#x2F;smartsubtract&#x2F;" rel="nofollow">https:&#x2F;&#x2F;oxfordwaveresearch.com&#x2F;products&#x2F;smartsubtract&#x2F;</a> which seems to do exactly the same but it&#x27;s not available for download.<p>Is there any (AI even?) tool that might do that? I tried an online AI tool which claimed it can extract voices but it returned back silence. I want to try OpenVino but not sure it will be useful with faint spoken words in a noisy environment with a song.
评论 #43069101 未加载
评论 #43093988 未加载
评论 #43069100 未加载
kmfrk3 个月前
I&#x27;m a big fan of RTX Voice, but it seems like the kind of feature you can only use in real-time as virtual audio and not as postprocessing. Anyone if Nvidia makes this possible?
pabs33 个月前
Wonder if these are open models like RNNoise now is.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;xiph&#x2F;rnnoise">https:&#x2F;&#x2F;github.com&#x2F;xiph&#x2F;rnnoise</a>