| Commit message (Expand) | Author | Age | |
|---|---|---|---|
| * | Fix audio normalizationHEADmaster | yum | 2023-04-04 |
| * | Begin work on evaluation framework | yum | 2023-03-03 |
| * | Add retainDuration option to CaptureParams | yum | 2023-02-26 |
| * | Normalize audio before sending to transcription layer | yum | 2023-02-26 |
| * | Frames with no VAD are shortened, not dropped | yum | 2023-02-26 |
| * | Bugfix, stereo PCM handling | Konstantin | 2023-01-28 |
| * | Minor, error handling | Konstantin | 2023-01-20 |
| * | Workaround for the Microsoft’s bug in their MP3 decoder MFT | Konstantin | 2023-01-19 |
| * | Minor, optimized away memcpy() when running audio capture | Konstantin | 2023-01-17 |
| * | Source codes | Konstantin | 2023-01-16 |
 |
index : TaSTT-Whisper.git | |
| High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model |
| summaryrefslogtreecommitdiffstats |