xiaobin-rong / gtcrn Goto Github PK
View Code? Open in Web Editor NEWThe official implementation of GTCRN, an ultra-lite speech enhancement model.
License: MIT License
The official implementation of GTCRN, an ultra-lite speech enhancement model.
License: MIT License
晓彬,您好:
非常感谢您的开源精神,我正在使用您开源的训练框架 SEtrain。
我发现训练出来的小参数网络在低信噪比场景下会出现降噪不干净,人声听感难受的问题。在尝试更换网络结构、更换mask、单独使用mse或sisnr均无明显改善,并且减小参数时问题更加明显。
您开源的本模型在处理低信噪比音频时同样会出现降噪不干净,听感难受的问题。您能否提出建议帮助解决这一问题。
期待回复,感谢!
I use the loss function in loss.py to train my network, but I get nan in some epoch, how can i fix this problem?
hello,man?
请问README Tabel1 跟Tabel2 中的RNNoise 的MACs 是怎么统计的呢? 单计算网络部分的话,不会有0.04(G/s) 这么大的, 我按你代码中的统计方式,如果按帧长512,帧移256 计算出来的Macs 为5.53M (约0.0055 G/s), 如果按帧长320, 帧移160计算出来的Macs为8.74M (约0.0087 G/s)
你好!多谢你的工作及开源!如果我想使用48k采样率,需要对模型代码进行修改吗,还是只需要改变输入数据即可。
祝您工作顺利!
首先非常感谢您的工作,我这里使用onnxsim.simplify导出时会报这个错
RuntimeError: /project/third_party/onnx-optimizer/onnxoptimizer/passes/eliminate_shape_gather.h:48: runTransform: Assertion 'indices_val < dims.size()' failed.
我和DeepVQE对比后排查了如下的地方:
chunk改切片
转置卷积去掉
groups去掉
空洞卷积去掉
layernorm去掉
均没有排查到原因,还是报上述的错
请问您找到问题在哪了吗
Hello 新年好, 请问下 Temporal Recurrent Attention的具体作用应该如何理解?
您好,恭喜您完成了一个非常棒的工作,同时非常感谢您无私的分享。
就像您说的这个模型参数和运算量都是非常低的,不知道有没有一个稍微大一点 参数和运算量的模型,同时能达到更好的效果,应该朝哪个方向调参?
谢谢!
您好,恭喜您完成了一个非常棒的工作并且被ICASSP 2024 收录。关于Subband Feature Extraction这一块中,您使用了nn.Unfold的操作,我想请教一下这一块的设计**和作用是什么?感谢您的回答!
Hi, what license is this code released under?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.