Skip to main content

Notice

Please note that most of the software linked on this forum is likely to be safe to use. If you are unsure, feel free to ask in the relevant topics, or send a private message to an administrator or moderator. To help curb the problems of false positives, or in the event that you do find actual malware, you can contribute through the article linked here.
Topic: [SUGGESTION] Neural Network-based "delossifyers" listening test (Read 424 times) previous topic - next topic
0 Members and 1 Guest are viewing this topic.

[SUGGESTION] Neural Network-based "delossifyers" listening test

Since NN-based "delossify" models are evolving quickly, it would be interesting to start some blind tests about their quality effectiveness:




The test could be performed by comparing (blindly) the lossless source and the "delossyfied" results of the compressed version of the source itself (to be more clear: lossless source -> lossy version -> delossyfied results).

Here are Apollo's colab and Spaces to start own inferencing tests (4 models available now):
- https://colab.research.google.com/github/jarredou/Apollo-Colab-Inference/blob/main/Apollo_Audio_Restoration_Colab.ipynb#scrollTo=xFqIYcKxVXyd
- https://huggingface.co/spaces/patriotyk/Apollo

More NN-based audio restoring resources available here.

Thanks in advance.
Hybrid Multimedia Production Suite will be a platform-indipendent open source suite for advanced audio/video contents production.
Official git: https://forart.it/HyMPS/

Re: [SUGGESTION] Neural Network-based "delossifyers" listening test

Reply #1
It would be great if we could have this software on our computers. I think that is the reason people are not really keen on testing these, because there is no exe file to run.
TAPE LOADING ERROR

 

Re: [SUGGESTION] Neural Network-based "delossifyers" listening test

Reply #2
It would be great if we could have this software on our computers. I think that is the reason people are not really keen on testing these, because there is no exe file to run.
...of course you can (if you have enough computing power)...

Anyway I've already asked Intel to integrate these models into their OpenVINO™ AI Plugins for Audacity;)
Hybrid Multimedia Production Suite will be a platform-indipendent open source suite for advanced audio/video contents production.
Official git: https://forart.it/HyMPS/