# To process a single file:
result = infer_file(
input_path="./path_to_file",
model_path="./model/path_to_model.pth",
index_path="", # Optional: specify path to index file if available
device="cuda:0", # Use cpu or cuda
f0method="harvest", # Choose between 'harvest', 'crepe', 'rmvpe', 'pm'
pitch=0, # Transpose setting
output="out.wav", # Output file path
index_rate=0.5,
filter_radius=3,
resample_sr=0, # Set to desired sample rate or 0 for no resampling.
rms_mix_rate=0.25,
protect=0.33,
version="v2"
)
It seems like infer.py expects "opt_path". Or it may be I got this wrong.
From infer.py:
This is the example in the readme: