---
license: mit
language:
- en
- de
- fr
- it
- nl
- multilingual
base_model: oliverguhr/fullstop-punctuation-multilingual-base
pipeline_tag: token-classification
library_name: coreml
tags:
- coreml
- punctuation-restoration
- token-classification
- xlm-roberta
- on-device
---

# fullstop-coreml

`oliverguhr/fullstop-punctuation-multilingual-base` (XLM-RoBERTa token-classification,
~0.3 B) converted to **CoreML** (fp16) for on-device punctuation restoration —
downloaded on first use and run locally through CoreML + `swift-transformers`.

This is a **format conversion only** — the weights are unchanged from the upstream
PyTorch model. The model is a verbatim **token classifier**: it emits one punctuation
label per token, so it can add punctuation (`. , ? - :`) but can never reword the
input. Capitalization is handled separately (a heuristic restorer is typically chained
after it).

## Label map (`id2label`)

| id | label | meaning |
|----|-------|---------|
| 0 | `""` | no punctuation |
| 1 | `.` | period |
| 2 | `,` | comma |
| 3 | `?` | question mark |
| 4 | `-` | dash |
| 5 | `:` | colon |

## Files (repo layout)

The repo root is the folder a loader consumes directly:

| File | Purpose |
|------|---------|
| `Fullstop.mlpackage/` | CoreML model bundle (compile before load) |
| `tokenizer.json` | XLM-R Unigram tokenizer (HuggingFace `tokenizers`) |
| `tokenizer_config.json` | tokenizer config |
| `special_tokens_map.json` | XLM-R special tokens (`<s>`, `</s>`, `<pad>`, `<unk>`, `<mask>`) |
| `config.json` | model config incl. `id2label` / `label2id` |

## Loading (Swift)

```swift
// 1. Snapshot the repo (swift-transformers Hub):
//    Hub.snapshot(from: Repo(id: "gregbarbosa/fullstop-coreml")) -> localDir
// 2. Compile + load the CoreML model, build the tokenizer from the same folder:
let compiled = try await MLModel.compileModel(at: localDir.appendingPathComponent("Fullstop.mlpackage"))
let model = try MLModel(contentsOf: compiled)
let tokenizer = try await AutoTokenizer.from(modelFolder: localDir)
```

Inference contract: feed `input_ids` (shape `[1, seq]`, natural length — no padding)
and `attention_mask`; the output logits are `[1, seq, 6]` → argmax per token yields the
label id above. Attach each **word's** punctuation from the label on its final subword
(token boundaries marked by the XLM-R `▁` U+2581 prefix); skip special tokens.

## Provenance

- **Source model:** [`oliverguhr/fullstop-punctuation-multilingual-base`](https://huggingface.co/oliverguhr/fullstop-punctuation-multilingual-base) (MIT)
- **Conversion:** PyTorch → ONNX → CoreML (fp16). Parity verified 15/15 labels identical
  to the PyTorch reference across the conversion fixtures; tokenizer parity re-verified
  on-device 2026-06-26.
- **Conversion harness:** `restore-bench` (standalone repo).

## License

MIT — same as the upstream model. Conversion produced by Greg Barbosa.

## Citation

```bibtex
@article{guhr-EtAl:2021:fullstop,
  title={FullStop: Multilingual Deep Models for Punctuation Prediction},
  author={Guhr, Oliver and Schumann, Anne-Kathrin and Bahrmann, Frank and B{\"o}hme, Hans Joachim},
  booktitle={Proceedings of the Swiss Text Analytics Conference 2021},
  month={June},
  year={2021},
  address={Winterthur, Switzerland},
  publisher={CEUR Workshop Proceedings},
  url={http://ceur-ws.org/Vol-2957/sepp_paper4.pdf}
}
```