Upload README.md with huggingface_hub

README.md

@@ -12,21 +12,33 @@ tags:
 
 Parler-TTS Mini safetensors + ONNX exports for RLX (probe ONNX removed).
 
-**Kind:** Converted / re-laid-out for RLX from an upstream checkpoint.
+| Field | Value |
+|---|---|
+| **Hub id** | [`eugenehp/parlertts`](https://huggingface.co/eugenehp/parlertts) |
+| **Kind** | Converted / re-laid-out for RLX from an upstream checkpoint. |
+| **RLX crate** | [`rlx-parlertts`](https://github.com/MIT-RLX/rlx-models/tree/main/crates/rlx-parlertts) |
+| **Upstream** | https://huggingface.co/parler-tts/parler-tts-mini-v1 |
 
-**Suggested Hub repo:** `eugenehp/parlertts`
+## Quick start
 
-**Upstream:** https://huggingface.co/parler-tts/parler-tts-mini-v1
-
-**RLX crate:** [`rlx-parlertts`](https://github.com/MIT-RLX/rlx-models/tree/main/crates/rlx-parlertts)
+```bash
+hf download eugenehp/parlertts --local-dir .
+cargo run -p rlx-parlertts --release -- --model-dir .
+```
 
-## Contents
+## File highlights
 
-Weight tensors and configs in this directory (see file listing on the Hub).
+- `model.safetensors` (3.3 GiB)
+- `onnx/decoder.onnx` (1.7 GiB)
+- `onnx/text_encoder.onnx` (1.3 GiB)
+- `parler-tts-mini-v1-Q4_0.gguf` (776.8 MiB)
+- `tokenizer.json` (2.3 MiB)
+- `config.json` (6.8 KiB)
+- `generation_config.json` (265 B)
 
 ## Run with RLX
 
-From [rlx-models](https://github.com/MIT-RLX/rlx-models) with this directory as the model path:
+Clone [rlx-models](https://github.com/MIT-RLX/rlx-models), place this repo under `weights/tts/parlertts` (or pass the path explicitly), then:
 
 ```bash
 cargo run -p rlx-parlertts --release -- --model-dir .
@@ -38,6 +50,6 @@ Apache License 2.0 — see `LICENSE`. Inherit upstream terms when redistributing
 
 Original weights and authorship: https://huggingface.co/parler-tts/parler-tts-mini-v1
 
-## Staging note
+## Maintenance
 
-Prepared from the local `weights/` tree in [rlx-models](https://github.com/MIT-RLX/rlx-models) for a future standalone Hub upload. Prefer fetching upstream when this is only a redistrib.
+Cards and LFS attrs are regenerated from the local `weights/` tree in [rlx-models](https://github.com/MIT-RLX/rlx-models) via `python3 scripts/prepare_weights_hf.py`.