Upload README.md with huggingface_hub

README.md

@@ -16,26 +16,21 @@ base_model: nvidia/parakeet-tdt-0.6b-v3
 
 ONNX export of [nvidia/parakeet-tdt-0.6b-v3](https://huggingface.co/nvidia/parakeet-tdt-0.6b-v3) for use with OpenVINO on Intel NPU.
 
-Includes the bundled NeMo mel spectrogram preprocessor (`nemo128.onnx`) for a self-contained pipeline.
+Includes the bundled NeMo mel spectrogram preprocessor (\) for a self-contained pipeline.
 
 ## Files
 
 | File | Size | Description |
 |------|------|-------------|
-| `encoder-model.onnx` + `.data` | ~2.5 GB | Conformer encoder (runs on NPU) |
-| `decoder_joint-model.onnx` | 73 MB | TDT joint decoder (runs on CPU) |
-| `nemo128.onnx` | 141 KB | Mel spectrogram preprocessor (onnxruntime CPU) |
-| `vocab.txt` | 94 KB | 8193-token vocabulary |
-| `config.json` | 97 B | Model metadata |
+| \ + \ | ~2.5 GB | Conformer encoder (runs on NPU) |
+| \ | 73 MB | TDT joint decoder (runs on CPU) |
+| \ | 141 KB | Mel spectrogram preprocessor (onnxruntime CPU) |
+| \ | 94 KB | 8193-token vocabulary |
+| \ | 97 B | Model metadata |
 
 ## Pipeline
 
-```
-Audio (16kHz float32)
-  -> nemo128.onnx (onnxruntime CPU) -> mel spectrogram [1, 128, T]
-  -> encoder-model.onnx (OpenVINO NPU) -> encoder features [1, 1024, T/8]
-  -> decoder_joint-model.onnx (OpenVINO CPU) -> TDT greedy decode -> text
-```
+
 
 ## Performance (Intel Core Ultra / Meteor Lake NPU)
 
@@ -50,9 +45,7 @@ Audio (16kHz float32)
 
 Used by [npu-whisper](https://github.com/goodsmileduck/npu-whisper) dictation engine:
 
-```bash
-python dictation_engine.py --model parakeet
-```
+
 
 ## Credits