Hugging Face's logo

ASLP-lab
/
MeanVC

Audio-to-Audio
English
Chinese
DiT
Model card Files
xet
Community
1

Improve MeanVC model card: Update pipeline tag and add sample usage

#2
by nielsr HF Staff - opened
base: refs/heads/main
←
from: refs/pr/2
Discussion Files changed
+109
-81
nielsr

This PR significantly improves the model card for MeanVC by:

  • Correcting Metadata: The pipeline_tag is updated from the incorrect text-to-speech to audio-to-audio to accurately reflect its functionality as a voice conversion model. The erroneous text-to-speech tag is also removed.
  • Adding Comprehensive Sample Usage: A new "Sample Usage" section is added, directly incorporating the detailed "Getting Started" instructions (environment setup, model download, real-time and offline conversion code snippets) from the project's GitHub README. This makes it much easier for users to interact with and use the model.
  • Updating Image Paths: Relative image paths (figs/model.png, figs/[email protected]) are updated to absolute URLs on the Hugging Face Hub (https://huggingface.co/ASLP-lab/MeanVC/resolve/main/figs/model.png) for improved robustness and rendering.

These changes enhance the model's discoverability and provide users with clearer, more actionable information.

Improve MeanVC model card: Update pipeline tag and add sample usage7d74bca7
ASLP-lab changed pull request status to merged

Sign up or log in to comment