Add conversion scripts link and reproduce instructions

README.md

@@ -101,7 +101,18 @@ To use:
 
 ## Conversion
 
-Converted from PyTorch safetensors to CoreML using scripts forked from [FluidInference/mobius](https://github.com/FluidInference/mobius/tree/main/models/stt/qwen3-asr-0.6b/coreml), with dimensions updated for the 1.7B architecture.
+Conversion scripts are available at [alandotcom/caspi-hebrew-asr](https://github.com/alandotcom/caspi-hebrew-asr), forked from [FluidInference/mobius](https://github.com/FluidInference/mobius/tree/main/models/stt/qwen3-asr-0.6b/coreml) with dimensions updated for the 1.7B architecture.
+
+To reproduce:
+```bash
+git clone https://github.com/alandotcom/caspi-hebrew-asr.git
+cd caspi-hebrew-asr/conversion
+uv sync
+uv run python convert-qwen3-asr.py                    # full f32 conversion
+uv run python convert_decoder_fused.py                 # fused stateful decoder
+uv run python extract_embeddings.py                    # embeddings + vocab
+uv run python quantize_model.py input.mlpackage output.mlpackage --dtype int8  # quantize
+```
 
 Conversion pipeline:
 1. Audio encoder: traced with coremltools, FP16 precision