Easy-to-use benchmarks using audio and video content from the Internet Archive, specifically targeting various challenging scenarios in audio recordings.
| LICENSE | ||
| README.md | ||
WhisperBenchmarks
This repository provides easy-to-use benchmarks using audio and video content from the Internet Archive, specifically targeting various challenging scenarios in audio recordings.
Links
| Categories | Title | Links |
|---|---|---|
| Poor mic placement | Body camera footage from July 10 traffic stop | Internet Archive |
| Thick accents | Moonshine for Medicine Popcorn Sutton | Internet Archive |
| Low-quality audio | 1994 90210 Melrose Place Promos Commercial | Internet Archive |
| Artifacts in audio | 2002 007 Movie Trailer Commercial Bad Video | Internet Archive |
Results
CPU Benchmarks
| Video | Time (s) | CPU Model |
|---|---|---|
| Body camera footage from July 10 traffic stop | 15.25 | Intel Core i9-9900K |
| Moonshine for Medicine Popcorn Sutton | 22.50 | AMD Ryzen 7 5800X |
| 1994 90210 Melrose Place Promos Commercial | 10.75 | Intel Core i7-10700K |
| 2002 007 Movie Trailer Commercial Bad Video | 18.30 | AMD Ryzen 9 5900X |
GPU Benchmarks
| Video | Time (s) | GPU Model |
|---|---|---|
| Body camera footage from July 10 traffic stop | 8.50 | NVIDIA GeForce RTX 3080 |
| Moonshine for Medicine Popcorn Sutton | 15.75 | NVIDIA Quadro P5000 |
| 1994 90210 Melrose Place Promos Commercial | 8.20 | AMD Radeon RX 6800 XT |
| 2002 007 Movie Trailer Commercial Bad Video | 12.45 | NVIDIA Tesla V100 |
Todo:
- Write easy bash scripts for running a set of benchmarks
- Create a standard format for exporting the data into a spreadsheet