WFST based decoding in DeepSpeech Pytorch

SeanNaren / deepspeech.pytorch

Speech Recognition using DeepSpeech2.

MIT License

2.1k stars 620 forks source link

WFST based decoding in DeepSpeech Pytorch #399

Closed Pradeep-Rangan closed 4 years ago

Pradeep-Rangan commented 5 years ago

Hello all,

Does deepspeech.pytorch supports WFST based decoding along with Greedy search and Beam search decoding? I am following a complex procedure of saving the posteriors generated at the output later of LSTM and feeding the log posteriors value to TLG.fst of Kaldi.

If there are any alternate solutions, I kindly request you to provide the information on the same.

I hope you do the needful.

Thanks and Regards Pradeep R PhD student Dept. of CSE IIT Kharagpur

stale[bot] commented 4 years ago

This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.