Upload README.md with huggingface_hub

README.md

@@ -63,10 +63,16 @@ This preview will remain permanently published. The two future production models
 
 ## Usage
 
-```python
-# Standalone Python inference with the shipped inference.py:
-# pip install torch torchaudio librosa soundfile huggingface_hub
+**Not a `from_pretrained` model.** StyleTTS2 is not a `transformers` architecture and this is
+a training checkpoint rather than an export, so the repository ships `inference.py` and that
+is the interface. Download the repository and run from inside it:
+
+```bash
+pip install torch torchaudio librosa soundfile huggingface_hub
+hf download agbalu/Matoub-82M --local-dir Matoub-82M && cd Matoub-82M
+```
 
+```python
 from inference import MatoubTTS
 
 tts = MatoubTTS.load()
@@ -204,9 +210,8 @@ The published file includes optimiser state and is resumable. A stripped inferen
 ## Reproduction
 
 ```bash
-make modal-matoub-pull                  # download checkpoint to artifacts/matoub/
-make release-matoub                     # stage for Hub release
-make push-matoub                       # upload to agbalu/Matoub-82M
+make modal-matoub TASK=pull             # download the checkpoint to artifacts/matoub/
+make push REPO=matoub                   # restage and upload to agbalu/Matoub-82M
 make infer-matoub TEXT="Azul fell-awen, amek i telliḍ taṣebḥit-a?"
 ```
 
@@ -226,6 +231,18 @@ His voice is inseparable from the survival of Kabyle as a spoken language in col
 
 The naming is homage; it implies no endorsement by anyone.
 
+## Citation
+
+```bibtex
+@software{agbalu_matoub_2026,
+  title  = {Matoub-82M: neural speech synthesis for Kabyle},
+  author = {AƔBALU},
+  year   = {2026},
+  url    = {https://huggingface.co/agbalu/Matoub-82M},
+  note   = {StyleTTS2 fine-tune of Kokoro-82M on 21,953 restored Common Voice clips; preview}
+}
+```
+
 ## Licence
 
 **Apache-2.0** on the weights and the code. The training data derives from Common Voice Kabyle (CC0); the Kokoro base weights are published under Apache-2.0. A permissive grant on weights makes no claim about the voice recordings they were trained on.