transformers.js/scripts/extra
Joshua Lochner ebd533531a
Add support for cross-encoder models (+fix token type ids) (#501)
* Formatting

* Update ESM pair template

* Fix token type ids

* Update JSDoc

* Cleanup

* Remove unused `prepare_model_inputs` function

* Move pad and truncate logic to helper functions

* Add static padding/truncation unit tests

* Fix padding/truncation

* Remove unused `add_token_types` function

* Reduce duplication

* `let` -> `const` where possible

* Add cross-encoder models
2024-01-04 18:37:26 +02:00
..
clap.py Add support for CLAP (`zero-shot-audio-classification`) and Audio Spectrogram Transformer (`audio-classification`) (#427) 2023-12-05 12:17:42 +02:00
clip.py Add support for computing CLIP image and text embeddings separately (Closes #148) (#227) 2023-08-01 14:01:04 +02:00
esm.py Add support for cross-encoder models (+fix token type ids) (#501) 2024-01-04 18:37:26 +02:00
marian.py New models and refactoring (#276) 2023-09-08 15:17:05 +02:00
siglip.py Add support for SigLIP models (#473) 2023-12-27 15:49:33 +02:00
speecht5.py Add support for `text-to-speech` (w/ Speecht5) (#345) 2023-10-23 16:31:46 +02:00
vits.py Add support for VITS (multilingual TTS) (#466) 2023-12-26 16:34:52 +02:00
wav2vec2.py Add support for chat templates (#408) 2023-12-18 17:00:50 +02:00
whisper.py Fix `CustomWhisperOnnxConfig` 2023-09-01 16:14:49 +02:00