OSError: Character label file (csv format) doesn`t exist : ../../../data/vocab/aihub_character_vocabs.csv #168
Description
python main.py --dataset_path $DATASET_PATH --vocab_dest $VOCAB_DEST --output_unit $OUTPUT_UNIT --preprocess_mode $PREPROCESS_MODE --vocab_size $VOCAB_SIZE
위의 코드를 실행하여 transcript.txt파일과 aihub_labels.csv파일을 생성하는 것 까지는 성공했습니다.
이후
python ./bin/main.py model=ds2 train=ds2_train train.dataset_path=$DATASET_PATH
코드를 실행하여 학습을 진행시켰는데
[2022-11-07 10:56:29,128][kospeech.utils][INFO] - Operating System : Linux 5.10.133+
[2022-11-07 10:56:29,128][kospeech.utils][INFO] - Processor : x86_64
[2022-11-07 10:56:29,129][kospeech.utils][INFO] - CUDA is available : False
[2022-11-07 10:56:29,129][kospeech.utils][INFO] - PyTorch version : 1.12.1+cu113
Error executing job with overrides: ['model=ds2', 'train=ds2_train', 'train.dataset_path=/content/drive/MyDrive/KoreanSpeech_dataset/KoreanSpeech_categori/KsponSpeech_01']
Traceback (most recent call last):
File "/content/drive/MyDrive/kospeech_lastest/bin/kospeech/vocabs/ksponspeech.py", line 126, in load_vocab
with open(label_path, 'r', encoding=encoding) as f:
FileNotFoundError: [Errno 2] No such file or directory: '../../../data/vocab/aihub_character_vocabs.csv'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/content/drive/MyDrive/kospeech_lastest/bin/main.py", line 162, in main
last_model_checkpoint = train(config)
File "/content/drive/MyDrive/kospeech_lastest/bin/main.py", line 85, in train
output_unit=config.train.output_unit,
File "/content/drive/MyDrive/kospeech_lastest/bin/kospeech/vocabs/ksponspeech.py", line 46, in init
self.vocab_dict, self.id_dict = self.load_vocab(vocab_path, encoding='utf-8')
File "/content/drive/MyDrive/kospeech_lastest/bin/kospeech/vocabs/ksponspeech.py", line 139, in load_vocab
raise IOError("Character label file (csv format) doesnt exist : {0}".format(label_path)) OSError: Character label file (csv format) doesnt exist : ../../../data/vocab/aihub_character_vocabs.csv
Set the environment variable HYDRA_FULL_ERROR=1 for a complete stack trace.
위와 같은 에러가 발생한 것을 확인했습니다.
aihub_character_vocabs.csv파일이 존재함에도 저런 에러가 생기네요..
해결 방법이 있을까요??