English to German MT Transformer model trained on Must-C using Espnet2
Abstract
# RESULTS## Environments- date: `Tue Jan 27 11:48:33 CET 2026`- python version: `3.8.20 | packaged by conda-forge | (default, Sep 30 2024, 17:52:49) [GCC 13.3.0]`- espnet version: `espnet 202503`- pytorch version: `pytorch 2.0.0`fatal: not a git repository (or any parent up to mount point /vol)Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).fatal: not a git repository (or any parent up to mount point /vol)Stopping at filesystem boundary (GIT_DISCOVERY_ACROSS_FILESYSTEM not set).- Git hash: `` - Commit date: `` ## decode_mt_mt_model_valid.acc.ave ### BLEU |dataset|score|verbose_score||---|---|---||decode_mt_mt_model_valid.acc.ave/dev.en-de|21.9|56.3/28.8/16.6/10.1 (BP = 0.958 ratio = 0.959 hyp_len = 24424 ref_len = 25468)||decode_mt_mt_model_valid.acc.ave/tst-COMMON.en-de|23.0|57.7/30.3/17.6/10.7 (BP = 0.960 ratio = 0.960 hyp_len = 41773 ref_len = 43494)||decode_mt_mt_model_valid.acc.ave/tst-HE.en-de|20.5|53.4/26.8/14.9/8.6 (BP = 0.993 ratio = 0.993 hyp_len = 10295 ref_len = 10366)|
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
- 27 January 2026
- Document type
- Dataset