Faster-whisper

Temporary change in the command to install faster-whisper due to a mistake in uploading to pypi.org.

Update to faster-whisper 0.10.0.

Bump to 2.2 due to one additional commit. Otherwise, same as version 2.1.

Broke out into more scripts for manageability.

Now checks of a CUDA device is present and only show it as an option if so.

Automatically detects the supported quantizations based on your CPU and CUDA device (if present), greatly simplifying user experience.

Added usage of YAML config file to settings.

Added the ability to choose the model size, quantization, and compute device on the fly. Beware, no guardrails yet. So if you choose "cuda" and you don't have an Nvidia GPU I can't guarantee how it'll behave.

To check which quantizations your cpu and gpu support, use my other tool [HERE](https://github.com/BBC-Esq/ctranslate2-compatibility-checker).

Create an issue if you would like see or work on additional features or find a bug.