crank
crank copied to clipboard
k2kobayashi
A toolkit for non-parallel voice conversion based on vector-quantized variational autoencoder
are there any detailed informations to all the parameters in the config files and how they affect the audio? ``` conf/mlfb_vqvae.yml cobf/mflb_vqvae.yml ``` I left it all on default and...
I trained the model and want to test it by converting new audio files using the new trained model? How should I approach this?
I cant start the training at stage 3 anymore: ``` # python -m crank.bin.train --flag train --n_jobs 10 --conf conf/mlfb_vqvae.yml --checkpoint None --scpdir data/scp --featdir data/feature --expdir exp # Started...
--voc GL did not work because griffin_lim.py could not find *.h5 for eval. A quick hack for Griffin-Lim to work.
I am have bunch of real voice file. Some of it has real bad quality. At stage 2, utils.py, convert_continuos_f0(...), start_f0 = f0[f0 != 0][0] I am get exception "index...
I am add debug print(...) somewhere, for example, in feature.py _open_wavf(...) for print wav file name. Sometimes I am see output, sometimes not. Оbviously this is multithread related error. P.S....
Since the VCC data is not commonly available could you either: * Release your pretrained models or * Add a VCTK / LibriSpeech recipe? (Since that data is available freely)
` Traceback (most recent call last): File "/opt/conda/lib/python3.7/runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "/opt/conda/lib/python3.7/runpy.py", line 85, in _run_code exec(code, run_globals) File "/data/crank/crank/bin/extract_feature.py", line 18, in from crank.feature import...
- [x] vcc2020 - [x] PWG - [ ] MCD - [ ] MOSNet - [x] vcc2018 - [x] PWG - [x] MCD - [x] MOSNet
Feature
- [x] Add GL and neural vocoder samples for vcc2020v1 and vcc2018 recipes. - [x] Implement objective evaluation stage - [ ] Modify CI Anything else?
Metadata
Owner
Metadata
A toolkit for non-parallel voice conversion based on vector-quantized variational autoencoder