based on Whisper [0] and Whisper.cpp [1], I created a comparison of transcription performance (quantitative metrics such as relative speed).

You can find the code in the Colab [2] and a blog post [3] containing a how-to guide and visualizations.

In the future, I'd love to add WER evaluation and visualizations based on ground-truth data.

Bonus: Normally you would log these results from Python to Weights & Biases, but there is a way to log even from C++ / the cli by using `subprocess`

Would love to know what you think of this comparison and what features / attributes you would like to see in a more sophisticated comparison.

Thanks!

[0]: https://news.ycombinator.com/item?id=32927360 [1]: https://news.ycombinator.com/item?id=33877893 [2]: https://colab.research.google.com/drive/1mXZUdIbvdNVOFRJaIhW... [3]: https://wandb.ai/hans-ramsl/gradient-dissent-transcription/r...