Following this doc to fine-tune conformer-ctc model.
In this, subword tokenzier used for conformer-ctc and character tokenzier used for quartznet.
can we use character tokenzier for conformer-ctc model?
If yes, how?
Following this doc to fine-tune conformer-ctc model.
In this, subword tokenzier used for conformer-ctc and character tokenzier used for quartznet.
can we use character tokenzier for conformer-ctc model?
If yes, how?
This doc is from NeMO. You can take a look at Nemo’s discussions board and feel free to post a question (From Introduction — NVIDIA NeMo)
For TAO 4.0, the user guide is in Speech Recognition With Conformer - NVIDIA Docs.
This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.