mjhanphd
mjhanphd
Also, is TIMIT the only one you've tried? The basic idea of seq2seq models is to let the model to learn the direct relationship between audio and transcript, without the...
Also I hope you share the source codes for data preparation part, rather than just showing a brief idea.
Thank you so much.
@WindQAQ I tried training char-based model on librispeech. But I stopped it after 7 days of training because it seemed like there's no more decrease in loss, which was staying...
In my 2nd test, it finished normally but weird thing is the resulting file contains only 2 decoding results, while the "test-clean.tfrecords" contains much more instances. I ran the command...