Comparing
371tti:fix-doc-load-onnxruntime-musl
(b23fbfb
) withmain
(0d7d72d
)-37%
- Improvement
- 2
- Regression
- 6
- Untouched
- 6
- Skipped
- 8
Unknown Walltime execution environment detected
Using the Walltime instrument on standard Hosted Runners will lead to inconsistent data. For the most accurate results, we recommend using CodSpeed Macro Runners: bare-metal machines fine-tuned for performance measurement consistency.Different runtime environments detected
Some benchmarks with significant performance changes were compared across different runtime environments, which may affect the accuracy of the results. Learn more about regression causes.Benchmarks
22 total
replace_mora_pitch[SHORT]
crates/voicevox_core/benches/benches.rs::nonblocking+20%
797.2 µs663.7 µs
replace_mora_pitch[SHORT]
crates/voicevox_core/benches/benches.rs::blocking+17%
709 µs607 µs
unload_and_load_vvm
crates/voicevox_core/benches/benches.rs::blocking-12%
1.7 s1.9 s
construct_open_jtalk
crates/voicevox_core/benches/benches.rs::nonblocking-27%
111.7 µs152.1 µs
construct_open_jtalk
crates/voicevox_core/benches/benches.rs::blocking-37%
68.3 µs108.9 µs
synthesis[SHORT]
crates/voicevox_core/benches/benches.rs::blocking-15%
2 s2.4 s
replace_phoneme_length[SHORT]
crates/voicevox_core/benches/benches.rs::blocking-25%
70.3 µs93.7 µs
synthesis[SHORT]
crates/voicevox_core/benches/benches.rs::nonblocking-16%
2 s2.4 s
test_blocking_tts
crates/voicevox_core_python_api/python/benches/test_tts.py0%
2.6 s*2.6 s
replace_phoneme_length[SHORT]
crates/voicevox_core/benches/benches.rs::nonblocking-2%
121 µs122.9 µs
test_asyncio_tts
crates/voicevox_core_python_api/python/benches/test_tts.py-2%
2.6 s*2.7 s
analyze_text[SHORT]
crates/voicevox_core/benches/benches.rs::blocking-6%
289.2 µs306.9 µs
analyze_text[SHORT]
crates/voicevox_core/benches/benches.rs::nonblocking-6%
330.1 µs352.4 µs
unload_and_load_vvm
crates/voicevox_core/benches/benches.rs::nonblocking-8%
2 s2.1 s
The benchmarks below were skipped, so their baseline results are used instead. If they were deleted in your codebase, archive them to remove them from the performance reports.
Learn more about archiving benchmarks
Learn more about archiving benchmarks
synthesis[LONG]
crates/voicevox_core/benches/benches.rs::nonblockingSkipped
7 s*
analyze_text[LONG]
crates/voicevox_core/benches/benches.rs::nonblockingSkipped
1.6 ms*
analyze_text[LONG]
crates/voicevox_core/benches/benches.rs::blockingSkipped
1.6 ms*
replace_phoneme_length[LONG]
crates/voicevox_core/benches/benches.rs::nonblockingSkipped
252.2 µs*
replace_mora_pitch[LONG]
crates/voicevox_core/benches/benches.rs::blockingSkipped
2.4 ms*
replace_phoneme_length[LONG]
crates/voicevox_core/benches/benches.rs::blockingSkipped
194.8 µs*
replace_mora_pitch[LONG]
crates/voicevox_core/benches/benches.rs::nonblockingSkipped
2.5 ms*
synthesis[LONG]
crates/voicevox_core/benches/benches.rs::blockingSkipped
6.9 s*
Commits
Click on a commit to change the comparison rangeBase
main
0d7d72d
+26.38%
docs: `load-onnxruntime`フラグのmuslターゲットに関する警告を追加
5261fb2
16 days ago
by 371tti-63.64%
Merge branch 'main' into fix-doc-load-onnxruntime-musl
b23fbfb
10 days ago
by qryxip