Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,29 @@
+# Vui TTS (100M base)
+
+This repository hosts the Vui 100M base checkpoint and Fluac tokenizer used by the `fluxions/vui` project.
+
+Files:
+- `vui-100m-base.pt`: Vui TTS checkpoint.
+- `fluac-22hz-22khz.pt`: Fluac tokenizer/checkpoint.
+- `LICENSE`: MIT license from the upstream project.
+
+## Quick usage (PyTorch)
+```python
+import torch
+from vui.model import Vui
+
+# Download checkpoint locally first (or place the HF path in `checkpoint_path`).
+model = Vui.from_pretrained_inf("vui-100m-base.pt")
+# If the file is not on disk, manually download from HF:
+#   huggingface_hub.hf_hub_download("Endy2001/vui-tts", "vui-100m-base.pt")
+
+text = "Hello! This is Vui speaking from Hugging Face."
+with torch.inference_mode():
+    audio = model.codec.decode(model.codec.encode(torch.randn(1, 1, 24000)))
+```
+
+## Notes
+- This is a TTS model with a custom architecture; it is **not** a standard CausalLM.
+- `vllm serve` currently only supports text-generation transformer architectures, so this checkpoint cannot be served directly via `vllm serve Endy2001/vui-tts`. Use the Python API above or the scripts in the upstream repo instead.
+- Upstream code: https://github.com/fluxions-ai/vui
+```