I’m just wondering how to get a vector of the decoder hypothesis after calculated the Beamscore.
https://deepspeech.readthedocs.io/en/v0.6.1/Python-API.html
Do you mean this?
Metadata.confidence()
Approximated confidence value for this transcription. This is roughly the sum of the acoustic model logit values for each timestep/character that contributed to the creation of this transcription.