Realtimestt

- added parameter **beam_size**
(int, default=5)
The beam size to use for beam search decoding
- added parameter **beam_size_realtime**
(int, default=3)
The beam size to use for real-time transcription beam search decoding.
- added parameter **initial_prompt**
(str or iterable of int, default=None)
Initial prompt to be fed to the transcription models.
- added parameter **suppress_tokens**
(list of int, default=[-1])
Tokens to be suppressed from the transcription output.
- added method **set_microphone**(microphone_on=True)
This parameter allows dynamical switching between recording from the input device configured in RealtimeSTT and chunks injected into the processing pipeline with the feed_audio-method

- added beam_size: int = 5 and beam_size_realtime: int = 3 parameters to AudioToTextRecorder constructor allowing faster (realtime) transcriptions by lowering the beamsizes
- added last_transcription_bytes containing the raw bytes from the last transcription
You can retrieve those bytes with recorder.last_transcription_bytes for further analysis, saving to file etc

- fixed [qsize issue](https://github.com/KoljaB/RealtimeSTT/issues/7#issuecomment-2016894792) for macOS
- upgrade requirements to torch 2.2.2

- added on_recorded_chunk callback to allow processing of audio chunks recorded from microphone by the client

- switched to torch.multiprocessing
- added compute_type (14), input_device_index (select input audio device) and gpu_device_index (select gpu device) parameters
- recorder.text() interruptable with recorder.abort()
- fix for 20

- added [example](https://github.com/KoljaB/RealtimeSTT/tree/master/example_browserclient) how to realtime transcribe from browser microphone
- large-v3 whisper model now supported (upgrade to faster_whisper 0.10.0)
- added feed_audio() and use_microphone parameter to feed chunks