examples/commonvoice_17_vi_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": "vi",
  "dataset_name": "common_voice_17_0",
  "dataset_size": 12705254,
  "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/vi/train/vi_train_0.tar": {
      "num_bytes": 69468160,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/dev/vi_dev_0.tar": {
      "num_bytes": 14479360,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/test/vi_test_0.tar": {
      "num_bytes": 34488320,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/other/vi_other_0.tar": {
      "num_bytes": 276172800,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/invalidated/vi_invalidated_0.tar": {
      "num_bytes": 11345920,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/vi/validated/vi_validated_0.tar": {
      "num_bytes": 144384000,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/train.tsv": {
      "num_bytes": 688189,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/dev.tsv": {
      "num_bytes": 184767,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/test.tsv": {
      "num_bytes": 373370,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/other.tsv": {
      "num_bytes": 3384906,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/invalidated.tsv": {
      "num_bytes": 111099,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/vi/validated.tsv": {
      "num_bytes": 1521796,
      "checksum": null
    }
  },
  "download_size": 556620178,
  "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": 569325432,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 1380061,
      "num_examples": 2298,
      "dataset_name": "common_voice_17_0"
    },
    "validation": {
      "name": "validation",
      "num_bytes": 375111,
      "num_examples": 641,
      "dataset_name": "common_voice_17_0"
    },
    "test": {
      "name": "test",
      "num_bytes": 754342,
      "num_examples": 1274,
      "dataset_name": "common_voice_17_0"
    },
    "other": {
      "name": "other",
      "num_bytes": 6857667,
      "num_examples": 11533,
      "dataset_name": "common_voice_17_0"
    },
    "invalidated": {
      "name": "invalidated",
      "num_bytes": 229034,
      "num_examples": 377,
      "dataset_name": "common_voice_17_0"
    },
    "validated": {
      "name": "validated",
      "num_bytes": 3109039,
      "num_examples": 5135,
      "dataset_name": "common_voice_17_0"
    }
  },
  "version": {
    "version_str": "17.0.0",
    "major": 17,
    "minor": 0,
    "patch": 0
  }
}