KeyError: 'hop_size'

Please help, it seems the hparams variable is not accessible from multiprocessing:

raceback (most recent call last):
File "", line 1, in
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 126, in _main
self = reduction.pickle.load(from_parent)
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 183, in
class MidiSingingBinarizer(SingingBinarizer):
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 242, in MidiSingingBinarizer
def get_align(ph_durs, mel, phone_encoded, res, hop_size=hparams['hop_size'], audio_sample_rate=hparams['audio_sample_rate']):
KeyError: 'hop_size'
Traceback (most recent call last):
File "", line 1, in
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 126, in _main
Traceback (most recent call last):
File "", line 1, in
self = reduction.pickle.load(from_parent)
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 116, in spawn_main
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 183, in
exitcode = _main(fd, parent_sentinel)
class MidiSingingBinarizer(SingingBinarizer):
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 126, in _main
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 242, in MidiSingingBinarizer
self = reduction.pickle.load(from_parent)
def get_align(ph_durs, mel, phone_encoded, res, hop_size=hparams['hop_size'], audio_sample_rate=hparams['audio_sample_rate']):
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 183, in
KeyError: 'hop_size'
class MidiSingingBinarizer(SingingBinarizer):
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 242, in MidiSingingBinarizer
def get_align(ph_durs, mel, phone_encoded, res, hop_size=hparams['hop_size'], audio_sample_rate=hparams['audio_sample_rate']):
KeyError: 'hop_size'
Traceback (most recent call last):
File "", line 1, in
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 126, in _main
self = reduction.pickle.load(from_parent)
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 183, in
class MidiSingingBinarizer(SingingBinarizer):
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 242, in MidiSingingBinarizer
def get_align(ph_durs, mel, phone_encoded, res, hop_size=hparams['hop_size'], audio_sample_rate=hparams['audio_sample_rate']):
KeyError: 'hop_size'
Traceback (most recent call last):
File "", line 1, in
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 126, in _main
self = reduction.pickle.load(from_parent)
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 183, in
class MidiSingingBinarizer(SingingBinarizer):
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 242, in MidiSingingBinarizer
def get_align(ph_durs, mel, phone_encoded, res, hop_size=hparams['hop_size'], audio_sample_rate=hparams['audio_sample_rate']):
KeyError: 'hop_size'
Traceback (most recent call last):
File "", line 1, in
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 116, in spawn_main
exitcode = _main(fd, parent_sentinel)
File "D:\Anaconda3\envs\svs\lib\multiprocessing\spawn.py", line 126, in _main
self = reduction.pickle.load(from_parent)
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 183, in
class MidiSingingBinarizer(SingingBinarizer):
File "D:\QIU\model_code\DiffSinger-master_new\DiffSinger-master\data_gen\singing\binarize.py", line 242, in MidiSingingBinarizer
def get_align(ph_durs, mel, phone_encoded, res, hop_size=hparams['hop_size'], audio_sample_rate=hparams['audio_sample_rate']):
KeyError: 'hop_size'

Start in data_gen/singing/binarize.py, especially the MidiSingingBinarizer.get_align definition at line 242 and the hparams initialization used when the module is imported. Reproduce the multiprocessing data-generation run and trace how hop_size is loaded; done means the worker starts without the reported KeyError.