MoonInTheRiver / MoonInTheRiver/DiffSinger
decoder part in e2e trainning using opencpop dataset
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
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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