TypeError: Object of type ndarray is not JSON serializable

[NekroniX588]

I try to use GigaAM-rnnt according this example https://colab.research.google.com/github/salute-developers/GigaAM/blob/main/examples/notebooks/GigaAM_RNNT_Model_Usage_Example.ipynb#scrollTo=nlrRmRPvKxYq

But i have error in this part

# Transcribing segments
BATCH_SIZE = 10
transcriptions = model.transcribe(segments, batch_size=BATCH_SIZE)[0]

Error:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
Cell In[18], line 2
      1 BATCH_SIZE = 10
----> 2 transcriptions = model.transcribe(segments, batch_size=BATCH_SIZE)[0]

File /opt/conda/envs/gigaam/lib/python3.10/site-packages/torch/utils/_contextlib.py:116, in context_decorator.<locals>.decorate_context(*args, **kwargs)
    113 @functools.wraps(func)
    114 def decorate_context(*args, **kwargs):
    115     with ctx_factory():
--> 116         return func(*args, **kwargs)

File /opt/conda/envs/gigaam/lib/python3.10/site-packages/nemo/collections/asr/models/rnnt_models.py:286, in EncDecRNNTModel.transcribe(self, paths2audio_files, batch_size, return_hypotheses, partial_hypothesis, num_workers, channel_selector, augmentor, verbose)
    284     for audio_file in paths2audio_files:
    285         entry = {'audio_filepath': audio_file, 'duration': 100000, 'text': ''}
--> 286         fp.write(json.dumps(entry) + '\n')
    288 config = {
    289     'paths2audio_files': paths2audio_files,
    290     'batch_size': batch_size,
   (...)
    293     'channel_selector': channel_selector,
    294 }
    296 if augmentor:

File /opt/conda/envs/gigaam/lib/python3.10/json/__init__.py:231, in dumps(obj, skipkeys, ensure_ascii, check_circular, allow_nan, cls, indent, separators, default, sort_keys, **kw)
    226 # cached encoder
    227 if (not skipkeys and ensure_ascii and
    228     check_circular and allow_nan and
    229     cls is None and indent is None and separators is None and
    230     default is None and not sort_keys and not kw):
--> 231     return _default_encoder.encode(obj)
    232 if cls is None:
    233     cls = JSONEncoder

File /opt/conda/envs/gigaam/lib/python3.10/json/encoder.py:199, in JSONEncoder.encode(self, o)
    195         return encode_basestring(o)
    196 # This doesn't pass the iterator directly to ''.join() because the
    197 # exceptions aren't as detailed.  The list call should be roughly
    198 # equivalent to the PySequence_Fast that ''.join() would do.
--> 199 chunks = self.iterencode(o, _one_shot=True)
    200 if not isinstance(chunks, (list, tuple)):
    201     chunks = list(chunks)

File /opt/conda/envs/gigaam/lib/python3.10/json/encoder.py:257, in JSONEncoder.iterencode(self, o, _one_shot)
    252 else:
    253     _iterencode = _make_iterencode(
    254         markers, self.default, _encoder, self.indent, floatstr,
    255         self.key_separator, self.item_separator, self.sort_keys,
    256         self.skipkeys, _one_shot)
--> 257 return _iterencode(o, 0)

File /opt/conda/envs/gigaam/lib/python3.10/json/encoder.py:179, in JSONEncoder.default(self, o)
    160 def default(self, o):
    161     """Implement this method in a subclass such that it returns
    162     a serializable object for ``o``, or calls the base implementation
    163     (to raise a ``TypeError``).
   (...)
    177 
    178     """
--> 179     raise TypeError(f'Object of type {o.__class__.__name__} '
    180                     f'is not JSON serializable')

TypeError: Object of type ndarray is not JSON serializable

According segment_audio function, segments are numpy array. But method model.transcribe waits paths.

Can you fix mistake in example and give code example to process long audios?