SpeechRecognition VS allosaurus

Start and Stop Listening Example

There is a great library that has support not only with OpenAIs whisper but many others that also work offline. https://github.com/Uberi/speech_recognition

This is the library: https://github.com/Uberi/speech_recognition

It is python remote plugin that is a tin wrapper around speech_recognition package.

I am less familiar with speech recognition myself. I have implemented something similar many years ago, back when Google had a REST API that allowed you to upload audio and they would respond with the recognized words/sentence. I think they still have the same API available, though. They limited how much you could send, but for voice commands it was pretty solid. However, SpeechRecognition looks like a library worth trying out for this, as that seems like it could do offline processing depending on the underlying library. They also have some examples to look at.

SpeechRecognition

I found this one here

https://github.com/Uberi/speech_recognition/blob/master/reference/library-reference.rst this might help. I guess your best bet is to rtfm.

Thank you for a great reply! If I catch your drift, how does this bode with phonemic transcription? Suppose we have an automatic phone recognizer tool such as Allosaurus.

And for phonemes recognition: - this looks like it could be useful (I'm sure you won't mind if it's "phones" instead of "phonemes"): https://github.com/xinjli/allosaurus - about using standard speech recognition tools: https://cmusphinx.github.io/wiki/phonemerecognition/