Update README.md

README.md

@@ -1,25 +1,33 @@
-# Svara TTS Submission - Team [Your Name/Team]
+---
+title: "Submission – Svara TTS API"
+emoji: 🎙️
+colorFrom: indigo
+colorTo: purple
+sdk: docker
+pinned: true
+app_file: Dockerfile
+---
 
-This repository contains the inference pipeline for the **Voice Tech for All** challenge. It serves a fine-tuned `kenpath/svara-tts-v1` model capable of synthesizing speech in 11 Indian languages via dynamic LoRA adapter switching.
+# 🎤 Svara TTS – Team Submission (FastAPI)
 
-## 🏗 Architecture
-- **Base Model:** `kenpath/svara-tts-v1` (Llama-based architecture predicting discrete audio codes).
-- **Vocoder:** `SNAC` (Multi-Scale Neural Audio Codec) at 24kHz.
-- **Adaptation:** 11 LoRA adapters loaded dynamically at runtime to minimize VRAM usage.
-- **Serving:** FastAPI server exposing a REST endpoint.
+This Space hosts the **Svara Text-to-Speech inference server** built using:
 
-## 🚀 Usage
+- **FastAPI** (HTTP API)
+- **Llama-based Svara TTS model**  
+- **SNAC 24kHz decoder (vocoder)**
+- **LoRA adapters** for multilingual synthesis  
+- **Dynamic adapter auto-discovery**
 
-### Endpoint: `POST /generate`
-Generates audio from text for a specific language.
+This Space is designed **specifically for judges** to test multilingual TTS output.
 
-**Parameters:**
-- `text` (string): The text to synthesize.
-- `language` (string): The language code (matches the adapter folder names, e.g., `hi`, `bn`).
+---
 
-**Example cURL:**
-```bash
-curl -X POST "[https://your-space-url.hf.space/generate](https://your-space-url.hf.space/generate)" \
-     -F "text=नमस्ते, आप कैसे हैं?" \
-     -F "language=hi" \
-     --output output.wav
+## 🚀 **Features**
+
+### ✔️ FastAPI backend
+Accessible programmatically using POST requests.
+
+### ✔️ Auto-discovers adapters
+Any folder inside `./adapters/<lang-code>/` is automatically loaded.
+
+Example: