examples/commonvoice_17_ta_asr/dataset_info.json

{
  "builder_name": "common_voice_17_0",
  "citation": "@inproceedings{commonvoice:2020,\n  author = {Ardila, R. and Branson, M. and Davis, K. and Henretty, M. and Kohler, M. and Meyer, J. and Morais, R. and Saunders, L. and Tyers, F. M. and Weber, G.},\n  title = {Common Voice: A Massively-Multilingual Speech Corpus},\n  booktitle = {Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020)},\n  pages = {4211--4215},\n  year = 2020\n}\n",
  "config_name": "ta",
  "dataset_name": "common_voice_17_0",
  "dataset_size": 221361139,
  "description": "Common Voice is Mozilla's initiative to help teach machines how real people speak. The dataset currently consists of 20408 validated hours of speech  in 124 languages, but more voices and languages are always added.",
  "download_checksums": {
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/n_shards.json": {
      "num_bytes": 17491,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/train/ta_train_0.tar": {
      "num_bytes": 1598955520,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/train/ta_train_1.tar": {
      "num_bytes": 224542720,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/dev/ta_dev_0.tar": {
      "num_bytes": 434257920,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/test/ta_test_0.tar": {
      "num_bytes": 454778880,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/other/ta_other_0.tar": {
      "num_bytes": 1560514560,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/other/ta_other_1.tar": {
      "num_bytes": 1515827200,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/other/ta_other_2.tar": {
      "num_bytes": 495831040,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/invalidated/ta_invalidated_0.tar": {
      "num_bytes": 231424000,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/validated/ta_validated_0.tar": {
      "num_bytes": 1447434240,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/validated/ta_validated_1.tar": {
      "num_bytes": 1530644480,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/validated/ta_validated_2.tar": {
      "num_bytes": 1654978560,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/ta/validated/ta_validated_3.tar": {
      "num_bytes": 652861440,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/train.tsv": {
      "num_bytes": 19608830,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/dev.tsv": {
      "num_bytes": 5203704,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/test.tsv": {
      "num_bytes": 4944646,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/other.tsv": {
      "num_bytes": 39470943,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/invalidated.tsv": {
      "num_bytes": 2499761,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/ta/validated.tsv": {
      "num_bytes": 56763398,
      "checksum": null
    }
  },
  "download_size": 11930559333,
  "features": {
    "context": {
      "sampling_rate": 16000,
      "_type": "Audio"
    },
    "instruction": {
      "dtype": "string",
      "_type": "Value"
    },
    "answer": {
      "dtype": "string",
      "_type": "Value"
    },
    "audio_length": {
      "dtype": "float64",
      "_type": "Value"
    },
    "language": {
      "dtype": "string",
      "_type": "Value"
    }
  },
  "homepage": "https://commonvoice.mozilla.org/en/datasets",
  "license": "https://creativecommons.org/publicdomain/zero/1.0/",
  "size_in_bytes": 12151920472,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 33336098,
      "num_examples": 45587,
      "dataset_name": "common_voice_17_0"
    },
    "validation": {
      "name": "validation",
      "num_bytes": 8797317,
      "num_examples": 12095,
      "dataset_name": "common_voice_17_0"
    },
    "test": {
      "name": "test",
      "num_bytes": 8556167,
      "num_examples": 12074,
      "dataset_name": "common_voice_17_0"
    },
    "other": {
      "name": "other",
      "num_bytes": 67773267,
      "num_examples": 93989,
      "dataset_name": "common_voice_17_0"
    },
    "invalidated": {
      "name": "invalidated",
      "num_bytes": 4282268,
      "num_examples": 5693,
      "dataset_name": "common_voice_17_0"
    },
    "validated": {
      "name": "validated",
      "num_bytes": 98616022,
      "num_examples": 135391,
      "dataset_name": "common_voice_17_0"
    }
  },
  "version": {
    "version_str": "17.0.0",
    "major": 17,
    "minor": 0,
    "patch": 0
  }
}