docs: add Python/optimum usage example, list source.spm and vocab.json in files table

README.md

@@ -41,12 +41,16 @@ MarianMT model trained on 9.78M Basque sentences that restores capitalization an
 |------|------|-------------|
 | `encoder_model_quantized.onnx` | 34 MB | Encoder (IR 8, int8 quantized) |
 | `decoder_model_merged_quantized.onnx` | 41 MB | Decoder with KV-cache (IR 8, int8 quantized) |
-| `tokenizer.json` | 2.1 MB | Custom Unigram + Metaspace pre-tokenizer |
+| `encoder_model.onnx` | 136 MB | Encoder (fp32, for reference / non-WASM use) |
+| `decoder_model_merged.onnx` | 160 MB | Decoder with KV-cache (fp32, for reference / non-WASM use) |
+| `tokenizer.json` | 2.1 MB | Custom Unigram + Metaspace pre-tokenizer (for Transformers.js) |
+| `source.spm` | 842 KB | SentencePiece model (for Python / HF MarianTokenizer) |
+| `vocab.json` | 2.1 MB | Vocab mapping (for Python / HF MarianTokenizer) |
 | `config.json` | 979 B | Model configuration |
 | `tokenizer_config.json` | 864 B | Tokenizer metadata |
 | `generation_config.json` | 288 B | Generation defaults |
 
-## Usage with Transformers.js
+## Usage with Transformers.js (browser)
 
 ```javascript
 import { pipeline } from '@huggingface/transformers';
@@ -62,6 +66,46 @@ console.log(result[0].translation_text);
 // → "Kaixo, zer moduz zaude?"
 ```
 
+## Usage with Python (ONNX Runtime via optimum)
+
+Install dependencies:
+
+```bash
+pip install optimum[onnxruntime] sentencepiece
+```
+
+Basic inference:
+
+```python
+from optimum.onnxruntime import ORTModelForSeq2SeqLM
+from transformers import AutoTokenizer, pipeline
+
+model_id = "itzune/txukun-cap-punct-eu"
+
+# Load int8 quantized ONNX model
+model = ORTModelForSeq2SeqLM.from_pretrained(
+    model_id,
+    encoder_file_name="encoder_model_quantized.onnx",
+    decoder_file_name="decoder_model_merged_quantized.onnx",
+    decoder_with_past_file_name="decoder_model_merged_quantized.onnx",
+    provider="CPUExecutionProvider",
+    use_cache=True,
+)
+
+# Tokenizer: load from our repo or HiTZ
+tokenizer = AutoTokenizer.from_pretrained("HiTZ/cap-punct-eu")
+
+# Create pipeline
+corrector = pipeline("translation", model=model, tokenizer=tokenizer, max_length=512)
+
+# Correct text
+result = corrector("euskal herrian euskaraz bizi nahi dugu")
+print(result[0]["translation_text"])
+# → "Euskal Herrian euskaraz bizi nahi dugu."
+```
+
+For a complete CLI tool using this model, see [txukun-cli](https://github.com/itzune/txukun-cli).
+
 ## Quantization details
 
 Dynamically quantized with `onnxruntime.quantization.quantize_dynamic(QuantType.QInt8, extra_options={"EnableSubgraph": True})`. The `EnableSubgraph` flag traverses into the `If`-node subgraphs of the merged decoder, quantizing `MatMul` operations in both branches. Results: