Add Moonshine #34784
Merged
Add Moonshine #34784
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
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
xenova
reviewed
Dec 15, 2024
src/transformers/models/moonshine/convert_usefulsensors_to_hf.py
Outdated
Show resolved
Hide resolved
xenova
reviewed
Dec 16, 2024
xenova
reviewed
Dec 16, 2024
Co-authored-by: Joshua Lochner <admin@xenova.com>
|
Amazing work @eustlb and team! 🤗 |
ArthurZucker
pushed a commit
that referenced
this pull request
Jan 10, 2025
* config draft * full encoder forward * full decoder forward * fix sdpa and FA2 * fix sdpa and FA2 * moonshine model * moonshine model forward * fix attention with past_key_values * add MoonshineForConditionalGeneration * fix cache handling and causality for cross attention * no causal attention mask for the encoder * model addition (imports etc) * small nit * nits * Update src/transformers/models/moonshine/convert_usefulsensors_to_hf.py Co-authored-by: Joshua Lochner <admin@xenova.com> * add rope_theta * nits * model doc * Update src/transformers/models/auto/configuration_auto.py Co-authored-by: Joshua Lochner <admin@xenova.com> * imports * add MODEL_FOR_SPEECH_SEQ_2_SEQ_MAPPING_NAMES * updates modular * make * make fix-copies * ruff check examples fix * fix check_modular_conversion * nit * nits * nits * copied from -> imports * imports fix * integrate attention refacto * modular edge case * remove encoder * convolutions params in config * run modular_model_converter * make * Update docs/source/en/model_doc/moonshine.md Co-authored-by: Joshua Lochner <admin@xenova.com> * MoonshineModelTest * correct typo * make style * integration tests * make * modular convert * name conversion update (up_proj -> fc1 etc) * update config * update MLP * update attention * update encoder layer * update decoder layer * update convolutions parameters * update encoder * remove INPUTS_DOCSTRING * update decoder * update conditional generation * update pretrained model * imports * modular converted * update doc * fix * typo * update doc * update license * update init * split config in file * two classes for MLP * attention from GLM * from GlmRotaryEmbedding * split MLP * apply arthur's review suggestions * apply arthur's review suggestions * apply arthur's review suggestions * auto feature extractor * convert modular * fix + make * convert modular * make * unsplit config * use correct checkpoint * wrap generate * update tests * typos * make * typo * update doc --------- Co-authored-by: Joshua Lochner <admin@xenova.com>
|
please check usefulsensors/moonshine#81. there is an error when using huggingface to load moonshine. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
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