diff options
| author | Konstantin <const@const.me> | 2023-01-16 23:28:54 +0100 |
|---|---|---|
| committer | Konstantin <const@const.me> | 2023-01-16 23:28:54 +0100 |
| commit | 5f11a8275d70dfd27b5998ab91b4ffb7b15ca418 (patch) | |
| tree | 3135ce4ad2d3e3234453156c83fb899873ea9bea /SampleClips/Readme.txt | |
| parent | 15aea5bccc5d03c15edc8acbdd1dacd6f2382caf (diff) | |
Sample audio clips, with performance stats
Diffstat (limited to 'SampleClips/Readme.txt')
| -rw-r--r-- | SampleClips/Readme.txt | 17 |
1 files changed, 17 insertions, 0 deletions
diff --git a/SampleClips/Readme.txt b/SampleClips/Readme.txt new file mode 100644 index 0000000..69432f4 --- /dev/null +++ b/SampleClips/Readme.txt @@ -0,0 +1,17 @@ +This folder contains 2 sample speech audio clips, `jfk.wav` and `columbia.wma` + +jfk.wav is from whisper.cpp repository. + +columbia.wma is from Wikipedia: https://upload.wikimedia.org/wikipedia/commons/1/1f/George_W_Bush_Columbia_FINAL.ogg +I had to re-encoded the audio from Ogg Vorbis into Windows Media Audio, because Media Foundation is unable to decode Vorbis. + +The rest of the text files in this folder are the outputs of the in-app performance profiler, when the app was transcribing these two audio clips on two different computers. + +The files names containing `1080ti` are from my desktop, which has nVidia GeForce 1080Ti GPU. + +The files names containing `vega7` are from my laptop, the GPU is integrated into AMD Ryzen 5 5600U processor. +The laptop model is HP ProBook 445 G8. While running the tests, the laptop was on battery power. + +The files names with `medium` in the middle were made with `ggml-medium.bin` Whisper model. + +The files with `large` were made with `ggml-large.bin` model.
\ No newline at end of file |