Note base model not on HuggingFace

README.md

@@ -126,7 +126,7 @@ Check the variant-specific `*.json` file for the exact state tensor shapes and o
 
 ## Credits
 
-- **Base model**: [LS-EEND](https://github.com/Audio-WestlakeU/FS-EEND) by Di Liang & Xiaofei Li (Westlake University). Paper: [LS-EEND: Long-Form Streaming End-to-End Neural Diarization with Online Attractor Extraction](https://arxiv.org/abs/2410.06670) (IEEE TASLP 2025).
+- **Base model**: [LS-EEND](https://github.com/Audio-WestlakeU/FS-EEND) by Di Liang & Xiaofei Li (Westlake University). Paper: [LS-EEND: Long-Form Streaming End-to-End Neural Diarization with Online Attractor Extraction](https://arxiv.org/abs/2410.06670) (IEEE TASLP 2025). The original model is not hosted on HuggingFace; pretrained weights are available on [GitHub](https://github.com/Audio-WestlakeU/FS-EEND).
 - **CoreML conversion**: [@GradientDescent2718](https://huggingface.co/GradientDescent2718). Original repo: [GradientDescent2718/ls-eend-coreml](https://huggingface.co/GradientDescent2718/ls-eend-coreml).
 
 ## Source project