BigVGAN benefits from 8 intra-op threads (all perf cores). Pre_conv and pre_transformer kept at 4T (small, less contention). BigVGAN: 2757ms → 1872ms (-885ms), decode total: 2830ms → 2035ms Pipeline: 6438ms → 5834ms → RTF 1.26 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| app | ||
| gradle/wrapper | ||
| COMPILE_WHISPER_NPU.md | ||
| RAPPORT_TTS_NPU.md | ||
| RAPPORT_TTS_QWEN3_TESTS.md | ||
| build.gradle.kts | ||
| gradle.properties | ||
| gradlew | ||
| gradlew.bat | ||
| settings.gradle.kts | ||