Using RVCBench

Read the documentation website · Project homepage · PyPI

Score generated speech, or evaluate a model on RVCBench data.

I want to…	Open
Install and run my first evaluation	Quickstart
Look up a command argument, its values or its default	CLI reference
Choose a paper scenario	Scenarios and task IDs
Score audio from my own dataset	Python API arguments and metric examples
Connect my model or use a batch inference script	Model evaluation
Set up GPU scoring or fix installation	Installation
Find dataset names and file formats	Datasets
Run a built-in model	Models and environments
Inspect or resume a run	Run guide
Reproduce the paper's results	Frozen v1 codebase

Run one scenario

After installation:

rvcbench tasks --suite core-v1
rvcbench prompts --suite core-v1 --tasks chinese --output prompts/
# Generate every prompt with your model in outputs/my-model/.
rvcbench score --suite core-v1 --tasks chinese \
  --generated outputs/my-model --output results/my-model --device cpu

Read results/my-model/submission.json for per-task scores. Replace chinese with task IDs, separated by spaces.

Contribute

See CONTRIBUTING for development checks and release validation, model integration for adding an adapter, and website maintenance for rebuilding the homepage.