I am running the sample speech.yml with audio file dataset describe on https://blog.deepgram.com/how-to-train-baidus-deepspeech-model-with-kur/
after running kur -v evaluate speech.yml , evaluate.pkl is genrated which when i unpickel , shows an np.array.
How do I get the desired output text file from the audio sample inputs?
I am running the sample speech.yml with audio file dataset describe on https://blog.deepgram.com/how-to-train-baidus-deepspeech-model-with-kur/
after running kur -v evaluate speech.yml , evaluate.pkl is genrated which when i unpickel , shows an np.array.
How do I get the desired output text file from the audio sample inputs?