Collection header: provenance, recipe, validation CER of the kept checkpoints

README.md

@@ -24,7 +24,7 @@ tags:
 
 All checkpoints are listed in the collection [https://huggingface.co/collections/ERISLab/listaya-slam-asr-projectors-on-tiny-aya-rocling-2026-6ab031414095f3df8805ed7b](https://huggingface.co/collections/ERISLab/listaya-slam-asr-projectors-on-tiny-aya-rocling-2026-6ab031414095f3df8805ed7b). The transcripts of their test-set evaluations are the dataset [ERISLab/LisTAya-transcripts](https://huggingface.co/datasets/ERISLab/LisTAya-transcripts).
 
-LisTAya (Listening Tiny Aya) is a family of speech-recognition models built with the SLAM-ASR recipe: a frozen Whisper-medium speech encoder, a frozen large-language-model decoder, and a trainable linear projector between them. Only the projector is trained. The checkpoints in this collection are the models behind the paper *How Does Regional Decoder Specialization Help Low-Resource ASR Based on the SLAM-ASR Framework?* (ROCLING 2026). Each checkpoint is one (language, decoder) cell of that study.
+LisTAya (Listening Tiny Aya) is a family of speech-recognition models built with the SLAM-ASR recipe: a frozen Whisper-medium speech encoder, a frozen large-language-model decoder, and a trainable linear projector between them. Only the projector is trained. The checkpoints in this collection are the models behind the paper *Does Regional Decoder Specialization Help Low-Resource ASR Based on the SLAM-ASR Framework?* (ROCLING 2026). Each checkpoint is one (language, decoder) cell of that study.
 
 ## Decoders