Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Hackathon 7th] fix Voc5/Jets/TTS2 with CSMSC #3906

Merged
merged 9 commits into from
Dec 2, 2024
Merged

[Hackathon 7th] fix Voc5/Jets/TTS2 with CSMSC #3906

merged 9 commits into from
Dec 2, 2024

Conversation

Liyulingyue
Copy link
Contributor

@Liyulingyue Liyulingyue commented Nov 22, 2024 •
edited
Loading

PR types

Others

PR changes

Others

Describe

  1. 修复文档表述问题
  2. 修复类型提升不支持的问题
  3. 调整预处理逻辑，适配小数据集

@paddle-bot Paddle-bot
Copy link

paddle-bot bot commented Nov 22, 2024

Thanks for your contribution!

@Liyulingyue Liyulingyue changed the title [Hackathon 7th] fix Voc5/Jets with CSMSC [Hackathon 7th] fix Voc5/Jets/TTS2 with CSMSC Nov 23, 2024
zxcd
zxcd reviewed Nov 25, 2024
View reviewed changes
paddlespeech/t2s/exps/fastspeech2/gen_gta_mel.py Outdated
# split data into 3 sections
num_train = 9800
num_dev = 100
# split data into 3 sections, the max number of dev/test is 10% or 100
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

在数据集固定的情况下，不建议进行修改

Liyulingyue
Liyulingyue commented Nov 30, 2024
View reviewed changes
paddlespeech/t2s/exps/fastspeech2/gen_gta_mel.py Outdated
Comment on lines 84 to 86
# split data into 3 sections, the max number of dev/test is 10% or 100
num_dev = min(int(len(wav_files) * 0.1), 100)
num_train = len(wav_files) - num_dev * 2
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
# split data into 3 sections, the max number of dev/test is 10% or 100
num_dev = min(int(len(wav_files) * 0.1), 100)
num_train = len(wav_files) - num_dev * 2
# split data into 3 sections
num_train = 9800
num_dev = 100

zxcd
zxcd approved these changes Dec 2, 2024
View reviewed changes
Copy link
Collaborator

@zxcd zxcd left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@zxcd zxcd merged commit 67ae7c8 into PaddlePaddle:develop Dec 2, 2024
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@zxcd zxcd zxcd approved these changes

Assignees
No one assigned
Labels
contributor Example README T2S
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@Liyulingyue @zxcd