Conversation
added 3 commits
June 30, 2026 19:54
…ations espeak-ng mispronounces many German abbreviations (reads them as words instead of spelling them letter-by-letter). The new de_abbrevs override section covers common Tagesschau/ARD news abbreviations: EU, USA, ARD, AKW, EZB, WHO, ADAC, IT, AFP, ÖPNV, OSZE, UEFA, FPÖ, etc. - Added de_overrides.json: de_abbrevs section (43 entries) - Updated _load_overrides() in de.py: includes de_abbrevs between en and de_foreign
UK is an English abbreviation that German speakers pronounce English-style
("ju-kej"), not with German letter names ("uː-kaː").
- CIA: German C (tseː) but English I (aɪ) and A (eɪ) → ˌtseːˌaɪˈeɪ - CEO: fully English → ˌsiːˌiːˈoː
dida-80b
force-pushed
the
feat/de-abbrevs
branch
from
June 30, 2026 17:54
ee9d3f4 to
75ee991
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
espeak-ng mispronounces many common German abbreviations by reading them as words instead of spelling them out letter-by-letter. For example:
IT→ˈiːt("it") instead ofˌiːˈteːÖPNV→ˈœpnfinstead ofˌøːˌpeːˌɛnˈfWOSZE→ˈɔsʦə("Osche") instead ofˌoːˌɛsˌtsɛtˈeːCEO→kˈeːoː("Keo") instead ofˌtseːˌeːˈoːFAZ→fˈɑːʦinstead ofˌɛfˌaːˈtsɛtSolution
Added a new
de_abbrevssection tode_overrides.jsonwith 43 entries covering abbreviations that espeak-ng consistently mispronounces. The section sits betweenenandde_foreignin priority order._load_overrides()inde.pyupdated accordingly:brand > en > de_abbrevs > de_foreign.Entries covered
News/politics: EU, USA, US, UN, ARD, ZDF (already handled), AKW, EZB, EVG, IAEA, WHO, ADAC, KI, AfD, IT, AFP, CEO, FAZ, OSZE, ÖVP, UEFA, AOK, FPÖ, ÖPNV, CGT, OPEC
Other: BASF, CIA, CO, CO2, ICE, IG, IS, IW, IWF, OECD, UK, UV, ZEW, AP, BA, UBS, SDAX, ESA
Letter name reference used
A=aː B=beː C=tseː D=deː E=eː F=ɛf G=ɡeː H=haː I=iː K=kaː L=ɛl M=ɛm N=ɛn O=oː P=peː R=ɛɾ S=ɛs T=teː U=uː V=fW W=veː X=ɪks Z=tsɛt Ö=øːIdentified via phoneme-gate mismatch analysis on Tagesschau TTS data (tagesschau_hf_40k).
🤖 Generated with Claude Code