Implement `whisper_token_to_bytes`

Not every token seems to be valid unicode but every token is interpreted
as such in `pw.whisper_token_to_str`. While this can be caught with an
exception handler it might be worthwhile to have a way of getting the
token bytes instead and parsing them using `.decode`, e.g.:

```python
str(pw.whisper_token_to_bytes(ctx, tid), 'utf8', 'ignore')
```