-
Notifications
You must be signed in to change notification settings - Fork 27.4k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[WIP] Add Moonshine #34784
base: main
Are you sure you want to change the base?
[WIP] Add Moonshine #34784
Conversation
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
bac9c9f
to
d0ed917
Compare
d4864c7
to
22dbaae
Compare
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
(just some notes in the meantime).
src/transformers/models/moonshine/convert_usefulsensors_to_hf.py
Outdated
Show resolved
Hide resolved
Co-authored-by: Joshua Lochner <[email protected]>
Co-authored-by: Joshua Lochner <[email protected]>
Indeed 😅 corrected, thanks !! |
# moonshine | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
# moonshine |
duplicate?
What does this PR do?
This PR adds support for Moonshine to the Transformers library.
Moonshine builds on top of Whisper’s architecture to overcome some of its limitations, primarily the restriction to a fixed 30-second audio window.
Key improvements in Moonshine’s architecture:
1. It uses SwiGLU activation instead of GELU in the decoder layers.
2. Most importantly, it replaces absolute position embeddings with Rotary Position Embeddings (RoPE), enabling Moonshine to process audio inputs of any length—unlike Whisper, which is limited to fixed 30-second windows.
Who can review?
@ArthurZucker
TODO
modular_moonshine.py