Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion datasets/flores/dataset_infos.json
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"neen": {"description": "Evaluation datasets for low-resource machine translation: Nepali-English and Sinhala-English.\n", "citation": "@misc{guzmn2019new,\n title={Two New Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English},\n author={Francisco Guzman and Peng-Jen Chen and Myle Ott and Juan Pino and Guillaume Lample and Philipp Koehn and Vishrav Chaudhary and Marc'Aurelio Ranzato},\n year={2019},\n eprint={1902.01382},\n archivePrefix={arXiv},\n primaryClass={cs.CL}\n}\n", "homepage": "https://github.com/facebookresearch/flores/", "license": "", "features": {"translation": {"languages": ["ne", "en"], "id": null, "_type": "Translation"}}, "supervised_keys": {"input": "ne", "output": "en"}, "builder_name": "flores", "config_name": "neen", "version": {"version_str": "1.1.0", "description": "", "datasets_version_to_prepare": null, "major": 1, "minor": 1, "patch": 0}, "splits": {"test": {"name": "test", "num_bytes": 1000483, "num_examples": 2836, "dataset_name": "flores"}, "validation": {"name": "validation", "num_bytes": 850660, "num_examples": 2560, "dataset_name": "flores"}}, "download_checksums": {"https://github.com/facebookresearch/flores/raw/master/data/wikipedia_en_ne_si_test_sets.tgz": {"num_bytes": 1542781, "checksum": "7a0245bb29fd03b46a1129831c183dfba0efc8452a9739d962759f25141aa648"}}, "download_size": 1542781, "dataset_size": 1851143, "size_in_bytes": 3393924}, "sien": {"description": "Evaluation datasets for low-resource machine translation: Nepali-English and Sinhala-English.\n", "citation": "@misc{guzmn2019new,\n title={Two New Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English},\n author={Francisco Guzman and Peng-Jen Chen and Myle Ott and Juan Pino and Guillaume Lample and Philipp Koehn and Vishrav Chaudhary and Marc'Aurelio Ranzato},\n year={2019},\n eprint={1902.01382},\n archivePrefix={arXiv},\n primaryClass={cs.CL}\n}\n", "homepage": "https://github.com/facebookresearch/flores/", "license": "", "features": {"translation": {"languages": ["si", "en"], "id": null, "_type": "Translation"}}, "supervised_keys": {"input": "si", "output": "en"}, "builder_name": "flores", "config_name": "sien", "version": {"version_str": "1.1.0", "description": "", "datasets_version_to_prepare": null, "major": 1, "minor": 1, "patch": 0}, "splits": {"test": {"name": "test", "num_bytes": 984947, "num_examples": 2767, "dataset_name": "flores"}, "validation": {"name": "validation", "num_bytes": 1032610, "num_examples": 2899, "dataset_name": "flores"}}, "download_checksums": {"https://github.com/facebookresearch/flores/raw/master/data/wikipedia_en_ne_si_test_sets.tgz": {"num_bytes": 1542781, "checksum": "7a0245bb29fd03b46a1129831c183dfba0efc8452a9739d962759f25141aa648"}}, "download_size": 1542781, "dataset_size": 2017557, "size_in_bytes": 3560338}}
{"neen": {"description": "Evaluation datasets for low-resource machine translation: Nepali-English and Sinhala-English.\n", "citation": "@misc{guzmn2019new,\n title={Two New Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English},\n author={Francisco Guzman and Peng-Jen Chen and Myle Ott and Juan Pino and Guillaume Lample and Philipp Koehn and Vishrav Chaudhary and Marc'Aurelio Ranzato},\n year={2019},\n eprint={1902.01382},\n archivePrefix={arXiv},\n primaryClass={cs.CL}\n}\n", "homepage": "https://github.com/facebookresearch/flores/", "license": "", "features": {"translation": {"languages": ["ne", "en"], "id": null, "_type": "Translation"}}, "post_processed": null, "supervised_keys": {"input": "ne", "output": "en"}, "task_templates": null, "builder_name": "flores", "config_name": "neen", "version": {"version_str": "1.1.0", "description": "", "major": 1, "minor": 1, "patch": 0}, "splits": {"validation": {"name": "validation", "num_bytes": 849380, "num_examples": 2560, "dataset_name": "flores"}, "test": {"name": "test", "num_bytes": 999063, "num_examples": 2836, "dataset_name": "flores"}}, "download_checksums": {"https://github.com/facebookresearch/flores/raw/master/floresv1/data/wikipedia_en_ne_si_test_sets.tgz": {"num_bytes": 1542781, "checksum": "7a0245bb29fd03b46a1129831c183dfba0efc8452a9739d962759f25141aa648"}}, "download_size": 1542781, "post_processing_size": null, "dataset_size": 1848443, "size_in_bytes": 3391224}, "sien": {"description": "Evaluation datasets for low-resource machine translation: Nepali-English and Sinhala-English.\n", "citation": "@misc{guzmn2019new,\n title={Two New Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-English},\n author={Francisco Guzman and Peng-Jen Chen and Myle Ott and Juan Pino and Guillaume Lample and Philipp Koehn and Vishrav Chaudhary and Marc'Aurelio Ranzato},\n year={2019},\n eprint={1902.01382},\n archivePrefix={arXiv},\n primaryClass={cs.CL}\n}\n", "homepage": "https://github.com/facebookresearch/flores/", "license": "", "features": {"translation": {"languages": ["si", "en"], "id": null, "_type": "Translation"}}, "post_processed": null, "supervised_keys": {"input": "si", "output": "en"}, "task_templates": null, "builder_name": "flores", "config_name": "sien", "version": {"version_str": "1.1.0", "description": "", "major": 1, "minor": 1, "patch": 0}, "splits": {"validation": {"name": "validation", "num_bytes": 1031158, "num_examples": 2899, "dataset_name": "flores"}, "test": {"name": "test", "num_bytes": 983563, "num_examples": 2767, "dataset_name": "flores"}}, "download_checksums": {"https://github.com/facebookresearch/flores/raw/master/floresv1/data/wikipedia_en_ne_si_test_sets.tgz": {"num_bytes": 1542781, "checksum": "7a0245bb29fd03b46a1129831c183dfba0efc8452a9739d962759f25141aa648"}}, "download_size": 1542781, "post_processing_size": null, "dataset_size": 2014721, "size_in_bytes": 3557502}}
2 changes: 1 addition & 1 deletion datasets/flores/flores.py
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@
}
"""

_DATA_URL = "https://github.com/facebookresearch/flores/raw/master/data/wikipedia_en_ne_si_test_sets.tgz"
_DATA_URL = "https://github.com/facebookresearch/flores/raw/master/floresv1/data/wikipedia_en_ne_si_test_sets.tgz"

# Tuple that describes a single pair of files with matching translations.
# language_to_file is the map from language (2 letter string: example 'en')
Expand Down