{
  "builder_name": "common_voice_16_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": "zh-CN",
  "dataset_name": "common_voice_16_0",
  "dataset_size": 423983727,
  "description": "Common Voice is Mozilla's initiative to help teach machines how real people speak. The dataset currently consists of 19159 validated hours of speech  in 119 languages, but more voices and languages are always added.",
  "download_checksums": {
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/n_shards.json": {
      "num_bytes": 17487,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/train/zh-CN_train_0.tar": {
      "num_bytes": 1157220864,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/dev/zh-CN_dev_0.tar": {
      "num_bytes": 436442624,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/test/zh-CN_test_0.tar": {
      "num_bytes": 506296320,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_0.tar": {
      "num_bytes": 1252570624,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_1.tar": {
      "num_bytes": 1216365056,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_2.tar": {
      "num_bytes": 1057693696,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_3.tar": {
      "num_bytes": 1037878784,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_4.tar": {
      "num_bytes": 1006488064,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_5.tar": {
      "num_bytes": 951297024,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_6.tar": {
      "num_bytes": 1054305280,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_7.tar": {
      "num_bytes": 1079122944,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_8.tar": {
      "num_bytes": 1057605632,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_9.tar": {
      "num_bytes": 1054744064,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_10.tar": {
      "num_bytes": 1037184512,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_11.tar": {
      "num_bytes": 1081821184,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_12.tar": {
      "num_bytes": 1144596992,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_13.tar": {
      "num_bytes": 1211527680,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_14.tar": {
      "num_bytes": 1190928384,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/other/zh-CN_other_15.tar": {
      "num_bytes": 299709952,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/invalidated/zh-CN_invalidated_0.tar": {
      "num_bytes": 1000983552,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/audio/zh-CN/invalidated/zh-CN_invalidated_1.tar": {
      "num_bytes": 416471552,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/train.tsv": {
      "num_bytes": 7373507,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/dev.tsv": {
      "num_bytes": 2567399,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/test.tsv": {
      "num_bytes": 2457920,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/other.tsv": {
      "num_bytes": 137605043,
      "checksum": null
    },
    "https://huggingface.co/datasets/fsicoli/common_voice_16_0/resolve/main/transcript/zh-CN/invalidated.tsv": {
      "num_bytes": 13622503,
      "checksum": null
    }
  },
  "download_size": 20414898643,
  "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": 20838882370,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 17963235,
      "num_examples": 29406,
      "dataset_name": "common_voice_16_0"
    },
    "validation": {
      "name": "validation",
      "num_bytes": 6351483,
      "num_examples": 10626,
      "dataset_name": "common_voice_16_0"
    },
    "test": {
      "name": "test",
      "num_bytes": 6263265,
      "num_examples": 10626,
      "dataset_name": "common_voice_16_0"
    },
    "other": {
      "name": "other",
      "num_bytes": 358056452,
      "num_examples": 610981,
      "dataset_name": "common_voice_16_0"
    },
    "invalidated": {
      "name": "invalidated",
      "num_bytes": 35349292,
      "num_examples": 58386,
      "dataset_name": "common_voice_16_0"
    }
  },
  "version": {
    "version_str": "15.0.0",
    "major": 15,
    "minor": 0,
    "patch": 0
  }
}