pytorch / pytorch/audio

I have some questions about RNNT loss.

Open
#3,750 6 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
2.9k
Forks
799
Avg merge
58m
Merged PRs (30d)
3

Description

hello
I would like to ask you a question that may be somewhat trivial.
The shape of logits of RNN T loss is Batch, max_seq_len, max_target_len+1, class.
Why is max_target_len+1 here?
Shouldn't the number of classes be +1 to the size of the total vocab? Because blank is included.
I don't understand at all.
Is there anyone who can help?

https://pytorch.org/audio/main/generated/torchaudio.functional.rnnt_loss.html

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the RNNT loss API documentation linked in the issue and review the documented logits shape and blank-token handling. Done means the relevant documentation clearly answers why max_target_len is incremented and how the blank class relates to the vocabulary.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.