Kazeia
/
kazeia
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
kazeia/scripts
History
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
..
cp_et_runner.cpp Initial commit: Kazeia TTS pipeline on NPU via ExecuTorch 2026-04-09 08:42:11 +02:00
export_cp_pte.py Initial commit: Kazeia TTS pipeline on NPU via ExecuTorch 2026-04-09 08:42:11 +02:00
export_talker_pte.py Restore KV=100 + fix as-is embeds + multi-segment support 2026-04-09 22:26:20 +02:00
prepare_tts_embeds.py Add prepare_tts_embeds.py for any text + codec_sum fix 2026-04-09 14:05:42 +02:00
prepare_tts_segments.py Restore KV=100 + fix as-is embeds + multi-segment support 2026-04-09 22:26:20 +02:00
qc_schema_serialize_patched.py Initial commit: Kazeia TTS pipeline on NPU via ExecuTorch 2026-04-09 08:42:11 +02:00
test_cp_et_quality.py Initial commit: Kazeia TTS pipeline on NPU via ExecuTorch 2026-04-09 08:42:11 +02:00