Upload README.md with huggingface_hub

README.md

@@ -2,28 +2,33 @@
 
 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.
+Contents:
+- `vui-100m-base.pt`: Vui TTS checkpoint (100M parameters).
+- `fluac-22hz-22khz.pt`: Fluac codec checkpoint.
 - `LICENSE`: MIT license from the upstream project.
 
-## Quick usage (PyTorch)
+## Quick usage (Python)
 ```python
 import torch
+from huggingface_hub import hf_hub_download
+from vui.inference import render
 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")
+# Download checkpoints from this repo (returns local file paths)
+ckpt = hf_hub_download("Endy2001/vui-tts", "vui-100m-base.pt")
+codec_ckpt = hf_hub_download("Endy2001/vui-tts", "fluac-22hz-22khz.pt")
+
+# Load model (pass codec checkpoint so it doesn't fetch from upstream)
+model = Vui.from_pretrained_inf(ckpt, codec_checkpoint=codec_ckpt).to("cuda")
 
 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)))
+    audio = render(model, text)[0].cpu().numpy()
+# `audio` is a mono waveform at 24 kHz
 ```
 
 ## 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.
+- `vllm serve` 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
 ```