Update README.md

README.md

@@ -17,7 +17,8 @@ tags:
 
 # Paradee-8M Pt-BR (Brazilian Portuguese)
 
-**Paradee-8M Pt-BR** is an ultra-lightweight Text-to-Speech (TTS) model for Brazilian Portuguese, with **7.88M parameters**, distilled from the Brazilian Portuguese voices of [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) (`pf_dora` and `pm_alex`) using the architecture of [Paradee-8M v1.2](https://huggingface.co/sahilmahendrakar/Paradee-8M-v1.2) by Sahil Mahendrakar.
+**Paradee-8M Pt-BR** is an ultra-lightweight Text-to-Speech (TTS) model for Brazilian Portuguese, with **7.88M parameters**, distilled from the Brazilian Portuguese voices of [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) (`pf_dora` and `pm_alex`) using the architecture of [Paradee-8M v1.2](https://huggingface.co/sahilmahendrakar/Paradee-8M-v1.2) by Sahil Mahendrakar and the paper 
+[Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model](https://huggingface.co/papers/2610.06817) .
 
 - **Ultra-lightweight:** The quantized `int8` ONNX model is only **8.46 MB** per voice (compared to >325 MB for Kokoro).
 - **Extremely fast:** Runs **~25x to 50x faster than real-time on a single CPU thread** (no GPU required). One second of speech is generated in ~20–40 ms.
@@ -254,11 +255,4 @@ Paradee decomposes the TTS pipeline into two independently distilled halves:
 }
 ```
 
-```bibtex
-@misc{mahendrakar2026paradee,
-  title  = {Paradee: Distilling Kokoro-82M into an 8M-Parameter Single-Voice Text-to-Speech Model},
-  author = {Mahendrakar, Sahil},
-  year   = {2026},
-  url    = {https://huggingface.co/sahilmahendrakar/Paradee-8M-v1.0}
-}
-```
+