Kazeia
/
kazeia
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
22 Commits 2 Branches 0 Tags 2.1 MiB
Commit Graph

2 Commits

Author SHA1 Message Date
Kazeia Team 3dcf73aa38 Restore KV=100 + fix as-is embeds + multi-segment support 
- KV_LEN restored to 100 (KV=64 caused quality loss from evicted role tokens)
- C++ uses pre-computed embeds as-is (no double codec_sum)
- Multi-segment format support in Kotlin (detects n_segments header)
- prepare_tts_segments.py: splits text + generates per-segment embeds
- Quality issue: Python-captured embeds differ from original working file
  (original was likely captured on-device, not from Python model.forward)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-09 22:26:20 +02:00
Kazeia Team 10a3904d7d Multi-segment TTS for long text: split → generate → concatenate 
- prepare_tts_segments.py: splits text at sentence boundaries,
  generates Python pre-computed embeds per segment
- Kotlin: detects multi-segment file format, processes each segment
  independently (fresh KV cache), concatenates audio
- Long text tested: 3 segments, 335 tokens, 26.8s audio, RTF 1.67

File format: n_segments, then per segment: nPrefill, nTotal, embeds[]

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-04-09 14:34:05 +02:00