Conversation
| texts: list[str], | ||
| audio_chunk_index: list[tuple[int, int | None]], | ||
| separator: str = " ", | ||
| ) -> list[str]: |
Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com>
|
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. |
| processor = AutoProcessor.from_pretrained("cohere-ai/cohere-asr") | ||
| model = CohereAsrForConditionalGeneration.from_pretrained("cohere-ai/cohere-asr", device_map="auto") |
There was a problem hiding this comment.
CohereLabs/cohere-transcribe-03-2026 :D
There was a problem hiding this comment.
and as it stands, the sample code has some issues complaining we need trust remote code due to custom tokenization
There was a problem hiding this comment.
yes this was not up to date ahah! always finishing with the doc 😅
|
@ArthurZucker the remaining failing is unrelated, ready to merge !! 😁 |
vasqu
left a comment
There was a problem hiding this comment.
Some quick comments for aligning a bit with modular maybe
|
[For maintainers] Suggested jobs to run (before merge) run-slow: auto, cohere_asr, parakeet |
* cohere-asr model * repo udpates * tmp weight mapping * add fast tests * fix compile * add integration tests * update integration tests * fixes * clearer API * test update * fix * cosmetics * fix on parakeet encoder * modular update * Update src/transformers/models/cohere_asr/configuration_cohere_asr.py Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * make check-repo * doc _reassemble_chunk_texts * nit * fix * updates * test update * make style * doc updates * ensure bc with the hub checkpoints * quick fixes * remove rope - not used * skip this one * fix * last fixes - needed revision + wrong main input name (less modular but we have to) * style * output_mask should be int! --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> Co-authored-by: vasqu <antonprogamer@gmail.com>
* cohere-asr model * repo udpates * tmp weight mapping * add fast tests * fix compile * add integration tests * update integration tests * fixes * clearer API * test update * fix * cosmetics * fix on parakeet encoder * modular update * Update src/transformers/models/cohere_asr/configuration_cohere_asr.py Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> * make check-repo * doc _reassemble_chunk_texts * nit * fix * updates * test update * make style * doc updates * ensure bc with the hub checkpoints * quick fixes * remove rope - not used * skip this one * fix * last fixes - needed revision + wrong main input name (less modular but we have to) * style * output_mask should be int! --------- Co-authored-by: Arthur <48595927+ArthurZucker@users.noreply.github.com> Co-authored-by: vasqu <antonprogamer@gmail.com>
What does this PR do?
Integration notes:
For now, this integration does not load mel filters from the checkpoint. The original model was trained backpropagating gradients in it, but we saw previously (with parakeet-ctc) that this does not affect performance much.
Benchmarks (WER):