Add pipeline tag, library_name and link to paper (#1)

- Add pipeline tag, library_name and link to paper (2fa824d82607cfe396880595d287fd9297e6b72f)


Co-authored-by: Niels Rogge <[email protected]>

README.md

@@ -1,7 +1,9 @@
 ---
 license: mit
+library_name: transformers
+pipeline_tag: voice-activity-detection
 tags:
-- speaker 
+- speaker
 - speaker-diarization
 - meeting
 - wavlm
@@ -12,7 +14,7 @@ tags:
 ---
 
 ## Overview
-This hub features the pre-trained model by [DiariZen](https://github.com/BUTSpeechFIT/DiariZen). The EEND component is built upon WavLM-Large and Conformer layers. The model was pre-trained on far-field, single-channel audio from a diverse set of public datasets, including AMI, AISHELL-4, AliMeeting, NOTSOFAR-1, MSDWild, DIHARD3, RAMC, and VoxConverse. Then structured pruning at 80% sparsity is applied. Finally, the pruned model is fine-tuned with [MLC-SLM](https://www.nexdata.ai/competition/mlc-slm) data. 
+This hub features the pre-trained model by [DiariZen](https://github.com/BUTSpeechFIT/DiariZen) as described in [BUT System for the MLC-SLM Challenge](https://huggingface.co/papers/2506.13414). The EEND component is built upon WavLM-Large and Conformer layers. The model was pre-trained on far-field, single-channel audio from a diverse set of public datasets, including AMI, AISHELL-4, AliMeeting, NOTSOFAR-1, MSDWild, DIHARD3, RAMC, and VoxConverse. Then structured pruning at 80% sparsity is applied. Finally, the pruned model is fine-tuned with [MLC-SLM](https://www.nexdata.ai/competition/mlc-slm) data. 
 
 
 ## Usage
@@ -57,4 +59,4 @@ DER evaluation of [Pyannote baseline](https://github.com/mubingshen/MLC-SLM-Base
 | Spanish            | 12.92    | 10.82    |
 | Thai               | 10.90    | 10.62    |
 | Vietnamese         | 14.64    | 12.69    |
-| **Average**        | **16.44**| **12.71**|
+| **Average**        | **16.44**| **12.71**|