English ASR Transformer trained on Must_C (English to German partition) using Espnet2
Abstract
# RESULTS## Environments- date: `Tue Jan 13 08:35:28 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` ### WER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err||---|---|---|---|---|---|---|---|---| |org/dev.en-de|1423|27590|90.5|5.8|3.7|2.2|11.7|61.6| |tst-COMMON.en-de|2641|47335|90.6|6.6|2.8|1.9|11.3|61.6||tst-HE.en-de|600|11536|92.3|5.5|2.2|1.5|9.2|54.7| ### CER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err||---|---|---|---|---|---|---|---|---||org/dev.en-de|1423|146991|93.9|1.8|4.3|2.3|8.4|61.6| |tst-COMMON.en-de|2641|251480|94.8|1.8|3.4|2.0|7.2|61.6||tst-HE.en-de|600|62010|96.1|1.5|2.4|1.5|5.4|54.7| ### TER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err||---|---|---|---|---|---|---|---|---||org/dev.en-de|1423|36650|88.9|4.9|6.2|2.3|13.4|61.6| |tst-COMMON.en-de|2641|61744|88.4|5.7|5.8|2.0|13.6|61.6||tst-HE.en-de|600|15278|90.8|4.8|4.5|1.7|10.9|54.7|
Fields of Study & Subjects
Speech Recognition and Synthesis
Natural Language Processing Techniques
Speech and Audio Processing
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 13 January 2026
- Document type
- Dataset