Upload README.md with huggingface_hub

README.md

@@ -6,6 +6,7 @@ tags:
   - automatic-speech-recognition
   - ggml
   - mobilint
+  - npu
 language:
   - en
   - zh
@@ -22,35 +23,52 @@ language:
 library_name: whisper.cpp
 ---
 
-# whisper.cpp GGML Models for Mobilint NPU
+# whisper.cpp Models for Mobilint NPU
 
-This repository provides GGML-format model files for use with [whisper.cpp-mblt](https://git.mobilint.com/algorithm-team/integration/whisper.cpp-mblt), the Mobilint NPU-accelerated fork of [whisper.cpp](https://github.com/ggml-org/whisper.cpp).
+This repository provides all model files needed to run [whisper.cpp-mblt](https://git.mobilint.com/algorithm-team/integration/whisper.cpp-mblt), the Mobilint NPU-accelerated fork of [whisper.cpp](https://github.com/ggml-org/whisper.cpp).
 
-## Available Models
+## Available Files
 
-| Model | File | Size | Parameters |
-|-------|------|------|------------|
-| whisper-small | `ggml-small.bin` | 466 MB | 244M |
+| Model | File | Size | Description |
+|-------|------|------|-------------|
+| whisper-small | `ggml-small.bin` | 466 MB | GGML model (tokenizer + weights for CPU fallback) |
+| whisper-small | `ggml-small-encoder.mxq` | 93 MB | Mobilint NPU encoder |
+| whisper-small | `ggml-small-decoder.mxq` | 159 MB | Mobilint NPU decoder |
 
 ## Usage
 
-The GGUF file provides the tokenizer vocabulary and embedding weights. For NPU inference, pair it with the MXQ files from [mobilint/whisper-small](https://huggingface.co/mobilint/whisper-small):
+### NPU Inference (Mobilint)
 
 ```bash
-# Auto-download from HuggingFace
-whisper-cli-mblt -hf mobilint/whisper-small -f audio.wav
-
-# Or manual paths
+# Download all files and run
 whisper-cli-mblt \
   -m ggml-small.bin \
-  --mxq-encoder whisper-small_encoder.mxq \
-  --mxq-decoder whisper-small_decoder.mxq \
+  --mxq-encoder ggml-small-encoder.mxq \
+  --mxq-decoder ggml-small-decoder.mxq \
   -f audio.wav
+
+# Or auto-download from HuggingFace
+whisper-cli-mblt -hf mobilint/whisper-small -f audio.wav
 ```
 
+### CPU Inference (standard whisper.cpp)
+
+The `ggml-small.bin` file is also compatible with standard whisper.cpp for CPU-only inference:
+
+```bash
+whisper-cli -m ggml-small.bin -f audio.wav
+```
+
+## Model Details
+
+- **Base model**: [openai/whisper-small](https://huggingface.co/openai/whisper-small) (244M parameters)
+- **Languages**: 99 languages supported (English, Chinese, German, Spanish, Russian, Korean, French, Japanese, Portuguese, Turkish, Polish, and more)
+- **Tasks**: Transcription and translation (to English)
+- **NPU pipeline**: Audio → mel spectrogram (CPU) → encoder (NPU, global4) → decoder (NPU, single core, greedy) → text
+
 ## Related Repositories
 
-- **[mobilint/whisper-small](https://huggingface.co/mobilint/whisper-small)** — Encoder and decoder MXQ files for Mobilint NPU
+- **[mobilint/whisper-small](https://huggingface.co/mobilint/whisper-small)** — Original Mobilint whisper-small model with config.json and tokenizer files
 - **[ggerganov/whisper.cpp](https://huggingface.co/ggerganov/whisper.cpp)** — Upstream GGML models for CPU inference
 
 ## License