Probe results: AquesTalk1 rejects U+FF01 ！, U+300C/D 「」, U+30FB ・,
U+3000 full-width space with error 105; only 、。？〜ー are safe.
User templates containing ！ (e.g. 卧槽！、是{uname}！...) now render
correctly: synthesize() final pass replaces any char outside the safe
kana/punctuation set with a 、 pause.
Verified: custom template full pipeline -> WAV 103316 bytes, no 105.
Rebuild portable zip (80.8 MB)
Root cause: AquesTalk_Synthe silently drops all text after a space.
English segments previously joined with spaces (word gap), so anything
after the first space was silent. Replace all spaces with 、 (Japanese
comma pause) which AquesTalk supports natively.
- PUNCT_MAP maps space -> 、
- convertEnglishSegment joins words with 、
- synthesize collapses consecutive pauses, strips residual spaces
Verified: 'Actually这个proposal是非常creative的' WAV 19316 -> 79196 bytes
- Add phonemize (MIT) rule-based G2P as second fallback tier
- IPA phoneme -> katakana CV-syllable transcription table
- proposal -> プラポーザル, bilibili -> バイリーバイリー (no more letter-spelling)
- Letter spelling kept as last resort only
- Bridge logs SYNTH IN/OUT to stderr; tts.py drains stderr to Python logs
so conversion results are visible in the server log
- Rebuild portable zip (83.8 MB)
chun_qiu