Document upstream attribution

README.md

@@ -36,6 +36,13 @@ base_model:
 - ResembleAI/chatterbox
 ---
 
+> **Mirror notice:** This KitsuMate repository is a server-side duplicate of
+> [`onnx-community/chatterbox-multilingual-ONNX`](https://huggingface.co/onnx-community/chatterbox-multilingual-ONNX)
+> at source revision `452d3f434aa592098f1eedac9099f33642ab2da5`. The model,
+> conversion work, documentation, license, and attribution remain credited to
+> ResembleAI and the ONNX Community contributors. KitsuMate does not claim
+> authorship of the mirrored artifacts.
+
 <img width="800" alt="cb-big2" src="https://github.com/user-attachments/assets/bd8c5f03-e91d-4ee5-b680-57355da204d1" />
 
 <h1 style="font-size: 32px">Chatterbox TTS</h1>
@@ -494,4 +501,4 @@ if __name__ == "__main__":
 Every audio file generated by Chatterbox includes [Resemble AI's Perth (Perceptual Threshold) Watermarker](https://github.com/resemble-ai/perth) - imperceptible neural watermarks that survive MP3 compression, audio editing, and common manipulations while maintaining nearly 100% detection accuracy.
 
 # Disclaimer
-Don't use this model to do bad things. Prompts are sourced from freely available data on the internet.
+Don't use this model to do bad things. Prompts are sourced from freely available data on the internet.