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.

  User Info

  Board Stats

  • Total Members: 0
  • Total Posts: 0
  • Total Topics: 0
  • Total Categories: 0
  • Total Boards: 0
  • Most Online: 21,221

  Theme Select



Forum Default

Permanently

  Board News

[OPEN SOURCE] FlowDec (by Meta Research)

2025-03-20 14:33:30 by forart.eu | Views: 539 | Comments: 0

FlowDec (ICLR 2025) is a full-band audio codec for general audio sampled at 48 kHz that combines non-adversarial codec training with a stochastic postfilter based on a novel conditional flow matching method.

From abstract:
Quote
Compared to the prior work ScoreDec which is based on score matching, we generalize from speech to general audio and move from 24 kbit/s to as low as 4 kbit/s, while improving output quality and reducing the required postfilter DNN evaluations from 60 to 6 without any fine-tuning or distillation techniques.

DEMO: https://sp-uhh.github.io/FlowDec/

License: Creative Commons Attribution-NonCommercial 4.0 International License
Official git: https://github.com/facebookresearch/FlowDec#readme


1 million posts!

2025-03-18 23:32:52 by spoon | Views: 1301 | Comments: 9

Hydrogen Audio has now accumulated over a million posts, 100,000 topics and 125K members.

It has also been running for close to 25 years.

Certainly has the legs, and here to stay.

[OPEN SOURCE] corticod (neural multimedia cocec)

2025-03-17 10:26:32 by forart.eu | Views: 1684 | Comments: 12

Publishing date: Jan 21, 2025
corticod is a biomimetic cortical coding library designed for hierarchical data processing, pattern recognition, and sequential data compression. It models a neural-inspired tree structure for adaptive learning and sparse representation of data.

  • A neural multimedia codec, currently tested for audio coding. Have comparable performance to current state-of-the-art lossy audio codecs (MP3, AAC, OPUS, OGG).

Official git: https://github.com/itu-lab/CorticalCodingCodec#readme