daa-tokenizers / results /dataset_stats.json
Ouaill's picture
Upload results/dataset_stats.json with huggingface_hub
07b7716 verified
Raw
History Blame Contribute Delete
2.51 kB
[
{
"dataset": "DODa",
"repo": "atlasia/DODa",
"text_col": "darija",
"total_rows": 87741,
"total_processed": 87741,
"ar": {
"count": 0,
"min": 0,
"max": 0,
"mean": 0.0,
"median": 0.0
},
"az": {
"count": 87739,
"min": 2,
"max": 155,
"mean": 23.96,
"median": 21.0
},
"mi": {
"count": 2,
"min": 11,
"max": 12,
"mean": 11.5,
"median": 11.5
},
"ALL": {
"count": 87741,
"min": 2,
"max": 155,
"mean": 23.96,
"median": 21.0
}
},
{
"dataset": "Darija-Wiki",
"repo": "atlasia/Moroccan-Darija-Wiki-Dataset",
"text_col": "content",
"total_rows": 10044,
"total_processed": 10044,
"ar": {
"count": 9570,
"min": 31,
"max": 43065,
"mean": 761.42,
"median": 506.0
},
"az": {
"count": 1,
"min": 3616,
"max": 3616,
"mean": 3616.0,
"median": 3616.0
},
"mi": {
"count": 473,
"min": 66,
"max": 95926,
"mean": 2631.33,
"median": 914.0
},
"ALL": {
"count": 10044,
"min": 31,
"max": 95926,
"mean": 849.76,
"median": 508.0
}
},
{
"dataset": "Atlaset",
"repo": "atlasia/Atlaset",
"text_col": "text",
"total_rows": 1170963,
"total_processed": 1170963,
"ar": {
"count": 1082406,
"min": 3,
"max": 429082,
"mean": 783.54,
"median": 94.5
},
"az": {
"count": 9897,
"min": 3,
"max": 228575,
"mean": 204.23,
"median": 29.0
},
"mi": {
"count": 78660,
"min": 4,
"max": 96263,
"mean": 421.6,
"median": 115.0
},
"ALL": {
"count": 1170963,
"min": 3,
"max": 429082,
"mean": 754.33,
"median": 86.0
}
},
{
"dataset": "Ours (daa-pairs)",
"repo": "OiQ/daa-pairs",
"text_col": "arabic",
"total_rows": 112814,
"total_processed": 112814,
"ar": {
"count": 84293,
"min": 19,
"max": 153,
"mean": 65.97,
"median": 65.0
},
"az": {
"count": 43,
"min": 48,
"max": 94,
"mean": 69.49,
"median": 66.0
},
"mi": {
"count": 28478,
"min": 27,
"max": 143,
"mean": 68.94,
"median": 68.0
},
"ALL": {
"count": 112814,
"min": 19,
"max": 153,
"mean": 66.72,
"median": 66.0
}
}
]