[FEATURE] Phonon-1: | New STT

[dxcore35]

Problem

• Phonon-1: a new frontier in speech recognition per byte.
• A 782 million param model in a 415 MB download, more accurate than a Whisper 2x its size.
• Transcribe an hour of audio in about two minutes on a MacBook Air.
• Open weights, Apache 2.0, today.

Proposed solution

Fork > https://github.com/fermionresearch/phonon

[altic-dev]

Oooo interesting let me look into it. hows the review?

[dxcore35]

Haven't have time to test it it was release few hours before I informed you :)
It is English only STT tho

[github-actions]

This issue has been marked stale because it has had no activity for 5 days. It will be closed in 2 days if there is no further activity. Add the keep-open or pinned label to prevent automatic closure.

[github-actions]

Closing this issue because it remained inactive for 2 days after being marked stale.

[dxcore35]

@altic-dev Probably need to adjust to bot so it is not so ....