Add TTS abbreviation expansion (sth→something, sb→somebody, etc.)

Text is preprocessed before TTS to expand abbreviations like
sth., sb., etc., z.B., usw. so the speaker says the full word.

40+ abbreviations covered (EN + DE). Applied to all languages.
Audio cache cleared to regenerate with correct pronunciation.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Benjamin Admin
2026-04-27 00:07:46 +02:00
parent 198a0b2a0d
commit b495e63e6f

View File

@@ -23,6 +23,53 @@ TTS_SERVICE_URL = os.getenv("TTS_SERVICE_URL", "http://bp-compliance-tts:8095")
# Local cache directory for generated audio
AUDIO_CACHE_DIR = os.path.expanduser("~/Arbeitsblaetter/audio-cache")
# Abbreviations expanded before TTS (so the speaker says the full word)
_TTS_EXPANSIONS = {
"sth.": "something",
"sth": "something",
"sb.": "somebody",
"sb": "somebody",
"smth.": "something",
"smb.": "somebody",
"sbd.": "somebody",
"etc.": "etcetera",
"e.g.": "for example",
"i.e.": "that is",
"esp.": "especially",
"approx.": "approximately",
"vs.": "versus",
"nr.": "number",
"no.": "number",
"p.": "page",
"adj.": "adjective",
"adv.": "adverb",
"prep.": "preposition",
"pron.": "pronoun",
"pl.": "plural",
"sg.": "singular",
"syn.": "synonym",
"ant.": "antonym",
# DE
"usw.": "und so weiter",
"bzw.": "beziehungsweise",
"z.B.": "zum Beispiel",
"d.h.": "das heisst",
"vgl.": "vergleiche",
"ca.": "circa",
"evtl.": "eventuell",
"ggf.": "gegebenenfalls",
}
def _expand_abbreviations(text: str) -> str:
"""Expand abbreviations so TTS speaks the full word."""
import re
for abbr, full in _TTS_EXPANSIONS.items():
# Word-boundary aware replacement (case-insensitive)
pattern = re.escape(abbr)
text = re.sub(rf'\b{pattern}', full, text, flags=re.IGNORECASE)
return text
def _ensure_cache_dir():
os.makedirs(AUDIO_CACHE_DIR, exist_ok=True)
@@ -56,13 +103,16 @@ async def synthesize_word(
if os.path.exists(cached):
return cached
# Expand abbreviations before speaking
speak_text = _expand_abbreviations(text)
# Call Piper TTS service via /synthesize-direct (returns MP3, selects language correctly)
try:
async with httpx.AsyncClient(timeout=30.0) as client:
resp = await client.post(
f"{TTS_SERVICE_URL}/synthesize-direct",
json={
"text": text,
"text": speak_text,
"language": language,
},
)