[Whisper Addition] Add in Whisper Implementation

[pavanagrawal123]

This is a janky (but working) implementation for Whisper if anyone wants to try this on a non MacOS system.

You'll have to build the C++ version of Whisper from here: https://github.com/ggerganov/whisper.cpp (instructions are great on the upstream repo!)

Also, some small fixes in case you have a GPU w/ CUDA -- in some instances tensors were getting loaded on separate devices.

In order to use whisper, the top of file parameters will have to be changed.

[invictus2010]

This looks just like what I'm looking for! Any sense of why I get the following error though?

    hear_process = get_hear()
  File "main.py", line 89, in get_hear
    whisper_model_location])
  File "/Users/<name>/opt/anaconda3/lib/python3.7/subprocess.py", line 800, in __init__
    restore_signals, start_new_session)
  File "/Users/<name>/opt/anaconda3/lib/python3.7/subprocess.py", line 1551, in _execute_child
    raise child_exception_type(errno_num, err_msg, err_filename)
FileNotFoundError: [Errno 2] No such file or directory: '~/Users/<name>/projects/whisper.cpp/stream': '~/Users/<name>/projects/whisper.cpp/stream'

I've triple checked the path; I definitely have the stream binary at the location.

[invictus2010]

Changed it ../whisper.cpp/stream and error cleared. Disregard above!