Update README.md

README.md

@@ -1,5 +1,5 @@
 ---
-title: Clearwave Ai
+title: ClearWave AI
 emoji: 🎵
 colorFrom: blue
 colorTo: green
@@ -9,50 +9,5 @@ app_file: app.py
 pinned: false
 ---
 
-# 🎵 ClearWave AI
-
-**Professional 3-Department Audio Processing Pipeline**
-Runs 100% free on Hugging Face ZeroGPU (A10G · 24 GB VRAM)
-
-## What It Does
-
-Upload any audio file and ClearWave AI runs it through three AI departments:
-
-| Dept | Model | What it does |
-|------|-------|--------------|
-| 🎙️ Denoiser | DeepFilterNet3 | Removes background noise, EBU R128 normalisation |
-| 📝 Transcriber | Groq Whisper large-v3 | Speech-to-text, 10-20x faster than local Whisper |
-| 🌐 Translator | NLLB-200-distilled-600M | Offline translation, 200 languages |
-
-**Example:**
-```
-Input  : English audio "Hello this is a test"
-Original (EN)  : Hello this is a test
-Translated (TE): హలో ఇది ఒక పరీక్ష
-Total time     : ~6 seconds
-```
-
-## Setting Your Groq API Key
-
-1. Get a free key at [console.groq.com](https://console.groq.com)
-2. In your Space: **Settings → Variables and secrets → New secret**
-3. Name: `GROQ_API_KEY`, Value: your key (`gsk_...`)
-4. Save — Space restarts automatically
-
-Without a key, the app falls back to local Whisper small (still works, slower).
-
-## How to Use
-
-1. Upload any audio file (MP3, WAV, AAC, OGG, M4A, FLAC, M4A, OPUS...)
-2. Set Input Language (or leave as Auto Detect)
-3. Set Output Language
-4. Click **Process Audio**
-5. View results in the Text Results, Clean Audio, and Timings tabs
-
-## Supported Languages
-
-English · Telugu · Hindi · Tamil · Kannada (+ 195 more via NLLB-200)
-
-## Cost
-
-**$0** — Hugging Face ZeroGPU + Groq free tier (14,400s audio/day)
+# ClearWave AI
+3-Department Audio Pipeline: Denoise → Transcribe → Translate