---
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-tc-bible-big-poz-en
language:
  - id
  - ms
  - en
tags:
  - translation
  - ctranslate2
  - marian
  - int8
  - quantized
pipeline_tag: translation
---

# opus-mt-tc-bible-big-poz-en — CTranslate2 int8

An int8 [CTranslate2](https://github.com/OpenNMT/CTranslate2) conversion of
[Helsinki-NLP/opus-mt-tc-bible-big-poz-en](https://huggingface.co/Helsinki-NLP/opus-mt-tc-bible-big-poz-en)
(Malayo-Polynesian → English, transformer-big, OPUS-MT / Tatoeba-Challenge release 2024-08-17;
covers Indonesian, Malay and related languages).

Converted with:

```
ct2-transformers-converter (TransformersConverter, quantization="int8",
                            copy_files=["source.spm", "target.spm"])
```

## Quality (measured on this int8 artifact)

FLORES-200 devtest, id→en, 300 sentences, CPU: **chrF2 69.3 at beam 1** (69.9 at beam 4).
The original fp32 model reports chrF 0.684 on flores200-devtest, so int8 quantization is
essentially loss-free.

## Usage

```python
import ctranslate2, sentencepiece as spm

translator = ctranslate2.Translator("model_dir", compute_type="int8")
sp_src = spm.SentencePieceProcessor("model_dir/source.spm")
sp_tgt = spm.SentencePieceProcessor("model_dir/target.spm")

tokens = sp_src.encode("Kehidupan seorang bankir itu sulit.", out_type=str) + ["</s>"]
result = translator.translate_batch([tokens], beam_size=1)
print(sp_tgt.decode(result[0].hypotheses[0]))
```

## Attribution & license

Original model by the [Language Technology Research Group at the University of Helsinki](https://huggingface.co/Helsinki-NLP)
(OPUS-MT project), released under **Apache-2.0**. This repository redistributes a quantized
conversion of those weights under the same license. Please cite the
[OPUS-MT](https://aclanthology.org/2020.eamt-1.61/) and
[Tatoeba Translation Challenge](https://aclanthology.org/2020.wmt-1.139/) papers.