In PYPI SpeechRecognition, it states that the Package is only supported up to Python version 3.6
I have successfully got it working in Python 3.6. in the past. But now upgraded to Python3.9.1. SpeechRecognition does not work as it is not supported.
Does anyone know a good workaround (in Python) to handle SpeechRecognition that returns the text not an audio file?
Many thanks!!
Both Google and AWS will work, from my experience, Google is faster and more accurate but does not work as well with compressed file types, so you'd best go with a wav. If these solutions aren't applicable, you always can use a virtual environment with an older version of python.
I also read through their documentation and it said that versions 3.3+ are all supported, so maybe updating the library will fix your issue.
(for the Google and AWS transcription services I have created some handy toolkits which would make the process much easier)
Hope this helped!
