(gpt17) <my_linux_username>@<my_linux_username>-SAPA1F:~$ cd '/home/<my_linux_username>/Desktop/gpt-2-tensorflow2.0' 
(gpt17) <my_linux_username>@<my_linux_username>-SAPA1F:~/Desktop/gpt-2-tensorflow2.0$ python pre_process.py --data-dir="/home/<my_linux_username>/Desktop/gpt-2-tensorflow2.0/data" --vocab-size=32000
Pre-processing the text data.....
0it [00:00, ?it/s]
Training BytePair encoding......
0it [00:00, ?it/s]
sentencepiece_trainer.cc(160) LOG(INFO) Running command: --input=/home/<my_linux_username>/Desktop/gpt-2-tensorflow2.0/data/bpe_spm.tsv --model_prefix=/home/<my_linux_username>/Desktop/gpt-2-tensorflow2.0/data/bpe_model --input_format=tsv --vocab_size=32000 --user_defined_symbols=[SEP],[BOS],[EOS] --hard_vocab_limit=false --model_type=bpe --pad_id=0 --unk_id=1 --bos_id=-1 --eos_id=-1 --pad_piece=[PAD] --unk_piece=[UNK]
sentencepiece_trainer.cc(73) LOG(INFO) Starts training with : 
trainer_spec {
  input: /home/<my_linux_username>/Desktop/gpt-2-tensorflow2.0/data/bpe_spm.tsv
  input_format: tsv
  model_prefix: /home/<my_linux_username>/Desktop/gpt-2-tensorflow2.0/data/bpe_model
  model_type: BPE
  vocab_size: 32000
  self_test_sample_size: 0
  character_coverage: 0.9995
  input_sentence_size: 0
  shuffle_input_sentence: 1
  seed_sentencepiece_size: 1000000
  shrinking_factor: 0.75
  max_sentence_length: 4192
  num_threads: 16
  num_sub_iterations: 2
  max_sentencepiece_length: 16
  split_by_unicode_script: 1
  split_by_number: 1
  split_by_whitespace: 1
  split_digits: 0
  treat_whitespace_as_suffix: 0
  user_defined_symbols: [SEP]
  user_defined_symbols: [BOS]
  user_defined_symbols: [EOS]
  required_chars: 
  byte_fallback: 0
  vocabulary_output_piece_score: 1
  train_extremely_large_corpus: 0
  hard_vocab_limit: 0
  use_all_vocab: 0
  unk_id: 1
  bos_id: -1
  eos_id: -1
  pad_id: 0
  unk_piece: [UNK]
  bos_piece: <s>
  eos_piece: </s>
  pad_piece: [PAD]
  unk_surface:  ⁇ 
}
normalizer_spec {
  name: nmt_nfkc
  add_dummy_prefix: 1
  remove_extra_whitespaces: 1
  escape_whitespaces: 1
  normalization_rule_tsv: 
}
denormalizer_spec {}
trainer_interface.cc(325) LOG(INFO) SentenceIterator is not specified. Using MultiFileSentenceIterator.
trainer_interface.cc(186) LOG(INFO) Loading corpus: /home/<my_linux_username>/Desktop/gpt-2-tensorflow2.0/data/bpe_spm.tsv
trainer_interface.cc(381) LOG(INFO) Loaded all 0 sentences
trainer_interface.cc(396) LOG(INFO) Adding meta_piece: [PAD]
trainer_interface.cc(396) LOG(INFO) Adding meta_piece: [UNK]
trainer_interface.cc(396) LOG(INFO) Adding meta_piece: [SEP]
trainer_interface.cc(396) LOG(INFO) Adding meta_piece: [BOS]
trainer_interface.cc(396) LOG(INFO) Adding meta_piece: [EOS]
trainer_interface.cc(401) LOG(INFO) Normalizing sentences...
Traceback (most recent call last):
  File "pre_process.py", line 105, in <module>
    train()
  File "/home/<my_linux_username>/anaconda3/envs/gpt17/lib/python3.7/site-packages/click/core.py", line 829, in __call__
    return self.main(*args, **kwargs)
  File "/home/<my_linux_username>/anaconda3/envs/gpt17/lib/python3.7/site-packages/click/core.py", line 782, in main
    rv = self.invoke(ctx)
  File "/home/<my_linux_username>/anaconda3/envs/gpt17/lib/python3.7/site-packages/click/core.py", line 1066, in invoke
    return ctx.invoke(self.callback, **ctx.params)
  File "/home/<my_linux_username>/anaconda3/envs/gpt17/lib/python3.7/site-packages/click/core.py", line 610, in invoke
    return callback(*args, **kwargs)
  File "pre_process.py", line 99, in train
    train_byte_pair_encoding(vocab_size)
  File "pre_process.py", line 47, in train_byte_pair_encoding
    spm.SentencePieceTrainer.train(spmcmd)
  File "/home/<my_linux_username>/anaconda3/envs/gpt17/lib/python3.7/site-packages/sentencepiece.py", line 389, in _sentencepiece_trainer_train
    return SentencePieceTrainer.TrainFromString(arg)
  File "/home/<my_linux_username>/anaconda3/envs/gpt17/lib/python3.7/site-packages/sentencepiece.py", line 197, in TrainFromString
    return _sentencepiece.SentencePieceTrainer_TrainFromString(arg)
RuntimeError: Internal: /sentencepiece/src/trainer_interface.cc(402) [!sentences_.empty()]