search

p0p4k / pflowtts_pytorch

Unofficial implementation of NVIDIA P-Flow TTS paper
https://neurips.cc/virtual/2023/poster/69899
MIT License
198 stars 28 forks source link

TypeError: pflowTTS.synthesise() got an unexpected keyword argument 'spks' #7

Open kunibald413 opened 7 months ago

kunibald413 commented 7 months ago

to infer on custom model (single speaker), this is called: python pflow/cli.py --file $INPUT_FILE --checkpoint_path "$CHECKPOINT_PATH" --vocoder "hifigan_univ_v1" --spk $SPEAKERID

it loads custom model and vocoder

[!] Loading custom_model!
[+] custom_model loaded!
[!] Loading hifigan_univ_v1!

then throws this error TypeError: pflowTTS.synthesise() got an unexpected keyword argument 'spks'

at

  File "/pflow/pflow/cli.py", line 377, in unbatched_synthesis
    output = model.synthesise(

nothing is passed as prompt to pflowTTS.synthesise in the cli.py script. not fully clear what should be passed. If it's not a quick fix, is there a workaround meanwhile?

thanks for your time

p0p4k commented 7 months ago

ah i see, the cli.py is supposed to be my last priority, for now you can synthesize on the Jupyter notebook. Sorry for inconvenience.

p0p4k commented 7 months ago

Also edit the cli.py functions based on synthesis.ipynb would work.