voxprint-mirror-opus-mt-en-ru

Unmodified backup mirror of Helsinki-NLP/opus-mt-en-ru (commit bb09c99d180016eac6819df3dae68edb1690fdee), made for the Voxprint voice-cloning / audiobook app as a fallback download source for its offline translation.

• Original repository: https://huggingface.co/Helsinki-NLP/opus-mt-en-ru
• Original commit (pinned): bb09c99d180016eac6819df3dae68edb1690fdee
• Licence: Apache-2.0 (https://www.apache.org/licenses/LICENSE-2.0) - the same licence as the original.
• Attribution: Opus-MT models are by the Language Technology Research Group at the University of Helsinki (Helsinki-NLP), trained on OPUS data (J. Tiedemann, S. Thottingal: OPUS-MT - Building open translation services for the World, EAMT 2020).
• Credit: all rights to the model belong to its authors; this mirror is not affiliated with them.
• Files: byte-identical to the original at that commit (SHA-256 manifest: infra/model_mirrors.json in the Voxprint repository). Only the files the app needs are mirrored (config, tokenizer, source.spm/target.spm, vocab.json, pytorch_model.bin); the original's TensorFlow / Rust / Flax copies of the weights are left out. Only this README.md (model card) differs.

---

Original model card

opus-mt-en-ru

• source languages: en

• target languages: ru

• OPUS readme: en-ru

• dataset: opus

• model: transformer-align

• pre-processing: normalization + SentencePiece

• download original weights: opus-2020-02-11.zip

• test set translations: opus-2020-02-11.test.txt

• test set scores: opus-2020-02-11.eval.txt

Benchmarks