Papers › TEVR: Improving Speech Recognition by Token Entropy Variance Reduction
TEVR: Improving Speech Recognition by Token Entropy Variance Reduction
Hajo Nils Krabbenhöft, Erhardt Barth
This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w.r.t. to the language model. This takes advantage of the fact that if the language model will reliably and accurately predict a token anyway, then the acoustic model doesn't need to be accurate in recognizing it. We train German ASR models with 900 million parameters and show that on CommonVoice German, TEVR scores a very competitive 3.64% word error rate, which outperforms the best reported results by a relative 16.89% reduction in word error rate. We hope that releasing our fully trained speech recognition pipeline to the community will lead to privacy-preserving offline virtual assistants in the future.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Speech Recognition | Common Voice German | wav2vec 2.0 XLS-R 1B + TEVR (5-gram) | Test CER | 1.54% | #1 of 14 | Archive leaderboard | report |
| Speech Recognition | Common Voice German | wav2vec 2.0 XLS-R 1B + TEVR (5-gram) | Test WER | 3.64% | #1 of 14 | Archive leaderboard | report |
| Speech Recognition | Common Voice German | wav2vec 2.0 XLS-R 1B + TEVR (4-gram) | Test WER | 3.70% | #2 of 14 | Archive leaderboard | report |
| Speech Recognition | Common Voice German | wav2vec 2.0 XLS-R 1B (5-gram) | Test CER | 1.62% | #4 of 14 | Archive leaderboard | report |
| Speech Recognition | Common Voice German | wav2vec 2.0 XLS-R 1B (5-gram) | Test WER | 4.38% | #4 of 14 | Archive leaderboard | report |
| Speech Recognition | Common Voice German | wav2vec 2.0 XLS-R 1B + TEVR (no LM) | Test WER | 10.10% | #13 of 14 | Archive leaderboard | report |
| Speech Recognition | Common Voice German | wav2vec 2.0 XLS-R (no LM) | Test WER | 12.06% | #14 of 14 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections