Word transcription of TIMIT dataset

mravanelli / pytorch-kaldi

pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.

2.37k stars 446 forks source link

Word transcription of TIMIT dataset #249

Open shessam opened 3 years ago

shessam commented 3 years ago

How can word-level instead of phoneme-level speech recognition be done with the TIMIT dataset? I build and train models. On the other hand, I have only phoneme transcription. I want word transcription of audio files. Would you help me?

TParcollet commented 3 years ago

Hi, this should certainly be managed at the Kaldi level as labels and features are generated with Kaldi !