Upload README.md with huggingface_hub

README.md

@@ -1,21 +1,43 @@
 ---
 base_model: unsloth/orpheus-3b-0.1-ft
 tags:
-- text-generation-inference
-- transformers
-- unsloth
-- llama
+- text-to-speech
+- TTS
+- Bangla
+- Orpheus
+- fine-tuned
 license: apache-2.0
 language:
-- en
+- bn
+datasets:
+- utshobs/bangla-tts-v2
 ---
+# 🎙️ Orpheus 3B TTS — Bangla (Fine-tuned)
 
-# Uploaded finetuned  model
+This model is a **fine-tuned version of Orpheus 3B** specialized for **Bangla text-to-speech (TTS)**.
 
-- **Developed by:** utshobs
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/orpheus-3b-0.1-ft
+---
+
+## 🧠 Model Overview
+- **Base Model:** [unsloth/orpheus-3b-0.1-ft](https://huggingface.co/unsloth/orpheus-3b-0.1-ft)
+- **Fine-tuned Dataset:** [utshobs/bangla-tts-v2](https://huggingface.co/datasets/utshobs/bangla-tts-v2)
+- **Language:** Bengali (Bangla)
+- **Task:** Text-to-Speech (TTS)
+- **Framework:** Transformers + PyTorch
+
+---
+
+## 🚀 Quick Usage
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("utshobs/Orpheus_3B_TTS_Bangla_V4")
+model = AutoModelForCausalLM.from_pretrained("utshobs/Orpheus_3B_TTS_Bangla_V4")
+
+🪪 License
+
+Apache 2.0 License
+
+👤 Author
 
-This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+Fine-tuned and prepared by Utshob.
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)