French to English MT transformer model trained on CoVoST2 using Espnet2
Abstract
# RESULTS## Environments- date: `Tue Jan 13 08:27:40 CET 2026`- python version: `3.8.18 (default, Sep 11 2023, 13:40:15) [GCC 11.2.0]`- espnet version: `espnet 202402`- pytorch version: `pytorch 1.13.0`- Git hash: `d090a74e9b1a8953aba40a2c9af1f9791b8c1cd9` - Commit date: `Mon Jun 10 14:26:18 2024 +0000` ## decode_mt_mt_model_valid.acc.ave ### BLEU |dataset|score|verbose_score||---|---|---||/dev.fr-en|38.9|69.9/46.6/32.8/23.8 (BP = 0.974 ratio = 0.974 hyp_len = 132471 ref_len = 135992)||/test.fr-en|38.9|70.0/46.9/33.1/23.9 (BP = 0.969 ratio = 0.970 hyp_len = 135146 ref_len = 139340)|
Fields of Study & Subjects
Natural Language Processing Techniques
Speech Recognition and Synthesis
Topic Modeling
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 12 January 2026
- Document type
- Dataset