diff options
| author | Konstantin <const@const.me> | 2023-01-29 16:34:03 +0100 |
|---|---|---|
| committer | Konstantin <const@const.me> | 2023-01-29 16:34:03 +0100 |
| commit | 600cb13f9f4b02d9030f99fc379bdebebb64b65d (patch) | |
| tree | 434fef5d8168c3e6d6e5b7e54aa53c2c522916bd | |
| parent | 45e141ca505883277e8a5f65e04cdf8d915bc825 (diff) | |
Readme
| -rw-r--r-- | Readme.md | 3 |
1 files changed, 0 insertions, 3 deletions
@@ -132,9 +132,6 @@ and [explicit FP16](https://github.com/microsoft/DirectXShaderCompiler/wiki/16-B Automatic language detection is not implemented. -The original version implements “diarize” feature, they analyze stereo PCM to detect speaker based on the difference between left/right channels.<br/> -Despite my version preserves stereo PCM data over the pipeline, it doesn’t expose that data. - In the current version there’s high latency for realtime audio capture.<br/> Specifically, depending on voice detection the figure is about 5-10 seconds.<br/> At least in my tests, the model wasn’t happy when I supplied too short pieces of the audio.<br/> |