Diffio AI (@diffioai) profile picture

Audio restoration for podcasts. Visit https://nitter.cf/t.co/KxDOlns8Wq for more.

Colorado Springs
Joined November 2025
I like this idea a lot. Simple and clean. Rather than just having an equal weight residual sum of transformer layers, let each layer use attn to compute an weight for each previous layers residual. Allowing each layer of the transformer to build an appropriate input by weighting the sum of each input layer. arxiv.org/pdf/2603.15031
1
1
68
More word alignment backends added to github.com/Diffio-AI/CohereX
1
2
3
102
Cohere-transcribe with a whisperX style interface: github.com/Diffio-AI/CohereX
2
3
97
Word alignment error relative to SNR. See 馃Уfor details.
3
2
4
96
Codex Wrapped 2025 Total Tokens: 3,073,600,806 Total Messages: 1,782 Total Sessions: 512 Top model: GPT 5.2 Codex Total Estimated Cost: $814.14 Credit: @nummanali @moddi3io
98
Replying to @diffioai @Meta
Has anyone ever figured out how to get help from @Meta. I guess they're too busy spending all their money on gpus to take any of my money.
3
90
Replying to @Meta
@Meta Any chance I can get some help?
2
95
Demo of Diffio AI restoring audio
1
1
67
Restoring audio in a hurricane Diffio AI
46