Files
Richard Nagyfi 55a52fd61f Gutenberg eBook Crawler + Datasets (#1463)
* Added Gutenberg Crawler Notebook
- added configrable Jupyter Notebook with crawler + ability to save to parquet
- added README.md
- added requirements.txt for running in venv / collab
2023-02-11 11:38:14 +00:00

17 lines
426 B
Python

from datasets import concatenate_datasets, load_dataset
def load(languages: list = ["en", "de", "fr", "es", "it", "pt", "nl", "hu"]):
ds = None
for lang in languages:
if ds is None:
ds = load_dataset(f"sedthh/gutenberg_{lang}")
else:
ds = concatenate_datasets([ds, f"sedthh/gutenberg_{lang}"])
return ds
if __name__ == "__main__":
ds = load()
print(ds["train"])