MoonInTheRiver / MoonInTheRiver/DiffSinger

decoder part in e2e trainning using opencpop dataset

Open
#72 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
4.9k
Forks
826
PR merge metrics
No merged PRs in 30d

Description

In the e2e trainning mode of opencpop, skip_decoder is true and the decoder part is not trainned at all, right?
But in the inference, you still use run_decoder to get mel_out and use it as a start for q_sample, right?
Why run_decoder can also used here?

Is that why you use k=60 in cascade mode but k=1000 in e2e mode?

Contributor guide

No contributing guide indexed for this repository

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

Trace the e2e training and inference entry points for the opencpop dataset, focusing on skip_decoder, run_decoder, mel_out, and q_sample. Compare the cascade and e2e paths, including their k values, and document whether the observed decoder behavior is intended or identifies a defect.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.