MoonInTheRiver / MoonInTheRiver/DiffSinger

Missing file "popcs_statis.yaml"

Open
#54 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

Hello! Thank you for this great repo. I saw that there is a new midi version tutorial with the opencpop, but you also mentioned the vocoder need to be fine-tuned further, so I would like to try the popcs dataset for midi version. At the preparation stage, I changed the
export PYTHONPATH=.
CUDA_VISIBLE_DEVICES=0 python data_gen/tts/bin/binarize.py --config usr/configs/midi/cascade/opencs/aux_rel.yaml
Into
export PYTHONPATH=.
CUDA_VISIBLE_DEVICES=0 python data_gen/tts/bin/binarize.py --config usr/configs/midi/e2e/popcs/ds100_adj_rel.yaml
But when I run it, it turns out the binarize.py requires a file called"popcs_statis.yaml", which should in path "usr/configs/midi/cascade/popcs/popcs_statis.yaml". Would you mind telling me how to generate that file or could you upload that file?

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

Start with data_gen/tts/bin/binarize.py and the referenced usr/configs/midi/e2e/popcs/ds100_adj_rel.yaml configuration. Trace where popcs_statis.yaml is loaded and compare it with the referenced usr/configs/midi/cascade/popcs/popcs_statis.yaml path. Done means the popcs preparation command runs without the missing-file error, or the repository documents how to generate the file.

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
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.