Kazeia
/
kazeia
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
kazeia/executorch-custom
History
Kazeia Team 173606dae7 Stable: decoder 8T optimization + restore pre-computed embeds 
- BigVGAN: 8 threads (2757→1872ms), pre_conv/pre_transformer: 4 threads
- Restored pre-computed embeds format (codec_sum+text from Python)
- Text-only trailing embeds don't work: model needs codec_sum for EOS

For long phrases, pre-computed embeds must be generated from Python.
RTF 1.26 on short phrase.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 		2026-04-09 13:42:02 +02:00
..
Module.java Shared Module C++ pipeline: RTF 1.6 with perfect quality 2026-04-09 12:05:58 +02:00
cp_et_runner.cpp Native C++ pipeline: RTF 1.4 (was 3.6 in Java) 2026-04-09 10:09:32 +02:00
cp_et_test_client.cpp Native C++ pipeline: RTF 1.4 (was 3.6 in Java) 2026-04-09 10:09:32 +02:00
jni_layer_tts.cpp Stable: decoder 8T optimization + restore pre-computed embeds 2026-04-09 13:42:02 +02:00
tts_pipeline_jni.cpp Disable C++ pipeline (QNN non-deterministic), keep Java RTF 1.8 2026-04-09 11:42:49 +02:00