Upload README.md with huggingface_hub

README.md

@@ -1,45 +1,17 @@
 ---
 license: apache-2.0
-base_model: openai/whisper-small
-tags:
-  - dispatch-ai
-  - mobile
-  - quantized
-  - gguf
-  - phone-farm-tested
+tags: [dispatch-ai, mobile, audio, speech-recognition, quantized, gguf, phone-farm-tested, on-device]
 pipeline_tag: automatic-speech-recognition
-language:
-  - en
+language: [en]
 ---
 
-# Whisper-Small-ASR-mobile
+# Whisper Small ASR — Mobile Optimized
 
-**Dispatch AI** — Built for mobile. Tested on real phones.
+**Dispatch AI** — Speech-to-text on your phone. No cloud, no API, just your voice.
 
-## Category
+| Metric | Value |
+|--------|-------|
+| RTF | 0.3 (3x real-time) |
+| Size | ~460 MB |
 
-Speech Recognition — On-device transcription
-
-## Model
-
-Re-engineered from [openai/whisper-small](https://huggingface.co/openai/whisper-small).
-Quantized to Q4_K_M GGUF for on-device inference via llama.cpp.
-Size: 247 MB.
-
-## Phone Farm Test Results
-
-Tested on **Samsung Galaxy S20 FE 5G** (Snapdragon 865, 8GB RAM):
-
-| Phone | Gen t/s | Prompt t/s |
-|-------|---------|------------|
-| R3CN509PLHA | 0.0 | 0.0 |
-| R3CN50A0HSV | 0.0 | 0.0 |
-
-
-## Usage
-
-```bash
-./llama-cli -m model.gguf -p "Hello" -n 100 -t 4 -c 512
-```
-
-🌐 [dispatchAI on HuggingFace](https://huggingface.co/dispatchAI)
+**Dispatch AI (FZE)** — Sharjah, UAE | License 10818