search

k2kobayashi / crank

A toolkit for non-parallel voice conversion based on vector-quantized variational autoencoder
MIT License
169 stars 31 forks source link

ValueError: too many values to unpack (expected 3) #41

Closed talka1 closed 3 years ago

talka1 commented 3 years ago

stage 1 - 6 successfully worked. Stage 7 failed.

mcd log says following:


'''
# python -m crank.bin.evaluate_mcd --conf conf/mlfb_vqvae.yml --n_jobs 10 --spkr_conf conf/spkr.yml --outwavdir exp/mlfb_vqvae/eval_PWG_wav/100000/wav --featdir data/feature 
# Started at Sun Mar  7 19:34:38 UTC 2021
#
2021-03-07 19:34:41,647 (evaluate_mcd:117) INFO: number of utterances = 20
joblib.externals.loky.process_executor._RemoteTraceback: 
"""
Traceback (most recent call last):
  File "/usr/local/lib/python3.7/dist-packages/joblib/externals/loky/process_executor.py", line 431, in _process_worker
    r = call_item()
  File "/usr/local/lib/python3.7/dist-packages/joblib/externals/loky/process_executor.py", line 285, in __call__
    return self.fn(*self.args, **self.kwargs)
  File "/usr/local/lib/python3.7/dist-packages/joblib/_parallel_backends.py", line 595, in __call__
    return self.func(*args, **kwargs)
  File "/usr/local/lib/python3.7/dist-packages/joblib/parallel.py", line 263, in __call__
    for func, args, kwargs in self.items]
  File "/usr/local/lib/python3.7/dist-packages/joblib/parallel.py", line 263, in <listcomp>
    for func, args, kwargs in self.items]
  File "/content/drive/MyDrive/crank/crank/bin/evaluate_mcd.py", line 48, in calculate
    number, orgspk, tarspk = basename.split("_")
ValueError: too many values to unpack (expected 3)
"""

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/content/drive/MyDrive/crank/crank/bin/evaluate_mcd.py", line 151, in <module>
    main()
  File "/content/drive/MyDrive/crank/crank/bin/evaluate_mcd.py", line 131, in main
    for cv_path in converted_files
  File "/usr/local/lib/python3.7/dist-packages/joblib/parallel.py", line 1054, in __call__
    self.retrieve()
  File "/usr/local/lib/python3.7/dist-packages/joblib/parallel.py", line 933, in retrieve
    self._output.extend(job.get(timeout=self.timeout))
  File "/usr/local/lib/python3.7/dist-packages/joblib/_parallel_backends.py", line 542, in wrap_future_result
    return future.result(timeout=timeout)
  File "/usr/lib/python3.7/concurrent/futures/_base.py", line 435, in result
    return self.__get_result()
  File "/usr/lib/python3.7/concurrent/futures/_base.py", line 384, in __get_result
    raise self._exception
ValueError: too many values to unpack (expected 3)
# Accounting: time=11 threads=1
# Ended (code 1) at Sun Mar  7 19:34:49 UTC 2021, elapsed time 11 seconds

Whats is happening here?

unilight commented 3 years ago

@talka1 Sorry for this late reply. Are you using some custom datasets?

talka1 commented 3 years ago

Yes i created my own dataset of two speakers, each with 90 wav files. What could possibly cause this problem? I guess there are too many values being unpacked to the ammount of variables that are specified to it right? In this case the eval_wav files?

unilight commented 3 years ago

@talka1 If you run existing example recipes (e.g. vcc2018, vcc2020), you will find the converted filenames of the format <number>_org-<orgspk>_cv-<tarspk>.wav. Please check if the filenames are of the same format.

talka1 commented 3 years ago

Yes this worked.

All my wav files were named like:

"spkr1_000.wav"... and "spkr2_000.wav"...

So it generated: 

"spkr1_085_org-spkr2_cv-spkr1.wav"

instead of:

"085_org-spkr2_cv-spkr1.wav"

I had to rename this mistake in all the files and also all generated Files made in all the Stages.

Now it gave me an mcd calculation result:

# python -m crank.bin.evaluate_mcd --conf conf/mlfb_vqvae.yml --n_jobs 10 --spkr_conf conf/spkr.yml --outwavdir exp/mlfb_vqvae/eval_PWG_wav/200000/wav --featdir data/feature 
# Started at Sat Mar 20 12:46:53 UTC 2021
#
2021-03-20 12:46:55,748 (evaluate_mcd:117) INFO: number of utterances = 22
spkr1 spkr1 7.458
spkr1 spkr2 11.707
spkr2 spkr1 11.223
spkr2 spkr2 7.358
# Accounting: time=122 threads=1
# Ended (code 0) at Sat Mar 20 12:48:55 UTC 2021, elapsed time 122 seconds

But the MOSnet score prediction failed.

# python -m crank.bin.evaluate_mosnet --outwavdir exp/mlfb_vqvae/eval_PWG_wav/200000/wav 
# Started at Sat Mar 20 12:48:55 UTC 2021
#
Traceback (most recent call last):
  File "/usr/lib/python3.7/runpy.py", line 193, in _run_module_as_main
    "__main__", mod_spec)
  File "/usr/lib/python3.7/runpy.py", line 85, in _run_code
    exec(code, run_globals)
  File "/content/drive/MyDrive/crank/crank/bin/evaluate_mosnet.py", line 15, in <module>
    import speechmetrics
ModuleNotFoundError: No module named 'speechmetrics'
# Accounting: time=1 threads=1
# Ended (code 1) at Sat Mar 20 12:48:56 UTC 2021, elapsed time 1 seconds

So do I need to install a package called "speechmetrics"?

EDIT: Fixed it by installing the repository speechmetrics

For CPU:
pip install git+https://github.com/aliutkus/speechmetrics#egg=speechmetrics[cpu]
For GPU:
pip install git+https://github.com/aliutkus/speechmetrics#egg=speechmetrics[gpu]

These are the Mosnet Score Prediction:

# python -m crank.bin.evaluate_mosnet --outwavdir exp/mlfb_vqvae/eval_PWG_wav/200000/wav 
# Started at Sat Mar 20 13:23:29 UTC 2021
#
2021-03-20 13:23:29,411 (evaluate_mosnet:40) INFO: number of utterances = 22
Loaded  speechmetrics.absolute.mosnet
2021-03-20 13:23:32,553 (driver:121) INFO: Generating grammar tables from /usr/lib/python3.7/lib2to3/Grammar.txt
2021-03-20 13:23:32,577 (driver:121) INFO: Generating grammar tables from /usr/lib/python3.7/lib2to3/PatternGrammar.txt
spkr1 spkr1 2.900
spkr1 spkr2 2.577
spkr2 spkr1 2.814
spkr2 spkr2 2.502
# Accounting: time=14 threads=1
# Ended (code 0) at Sat Mar 20 13:23:43 UTC 2021, elapsed time 14 seconds