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.

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

Added HifiTTS data preprocessor #53

Merged
merged 1 commit into from
Dec 24, 2023
Merged

Conversation

zyingt
Copy link
Contributor

@zyingt zyingt commented Dec 21, 2023

HifiTTS dataset preprocessing script has been added in: Amphion/preprocessors/hifitts.py

@lmxue lmxue self-requested a review December 21, 2023 16:59
test_total_duration = 0
valid_total_duration = 0

for distribution, books2utts in tqdm(distribution2books2utts.items()):
Copy link
Collaborator

Choose a reason for hiding this comment

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

Adding the desc attribute for each tqdm like the following would make the progress more clear

    for distribution, books2utts in tqdm(
        distribution2books2utts.items(),
        desc=f"Distribution"
    ):


waveform, sample_rate = torchaudio.load(res["Path"])
duration = waveform.size(-1) / sample_rate
res["Duration"] = duration
Copy link
Collaborator

Choose a reason for hiding this comment

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

"Text" information is missing, which is required in the processed dataset json files for TTS task.

@lmxue lmxue merged commit b092344 into open-mmlab:main Dec 24, 2023
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants