Add pipeline tag

Hi! I'm Niels from the community science team at Hugging Face. This PR adds the `pipeline_tag: automatic-speech-recognition` to the model card's metadata to help users discover this model when filtering by task on the Hub. I've also included a link to the paper in the model card description.

README.md

@@ -1,23 +1,24 @@
 ---
-license: mit
-tags:
-  - speech-recognition
-  - speech-translation
-  - diffusion
-  - flow-matching
-  - asr
-  - s2tt
 language:
-  - en
-  - de
+- en
+- de
 library_name: pytorch
+license: mit
+pipeline_tag: automatic-speech-recognition
+tags:
+- speech-recognition
+- speech-translation
+- diffusion
+- flow-matching
+- asr
+- s2tt
 ---
 
 # ELF-S2T pretrained weights
 
 Pretrained checkpoints for **"Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation"**.
 
-Code: https://github.com/Sslnon/ELF-S2T
+[Paper](https://huggingface.co/papers/2606.10368) | [Code](https://github.com/Sslnon/ELF-S2T)
 
 ELF-S2T performs speech-to-text as audio-conditioned generation in a continuous
 text-embedding space (a frozen Whisper-large-v3 encoder + a single linear
@@ -70,4 +71,4 @@ checkpoint's embedded `config`, so the same command works for every file.
       primaryClass={cs.SD},
       url={https://arxiv.org/abs/2606.10368}, 
 }
-```
+```