examples/commonvoice_17_th_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": "th",
  "dataset_name": "common_voice_17_0",
  "dataset_size": 271837409,
  "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/th/train/th_train_0.tar": {
      "num_bytes": 838082560,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/dev/th_dev_0.tar": {
      "num_bytes": 323399680,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/test/th_test_0.tar": {
      "num_bytes": 335851520,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_0.tar": {
      "num_bytes": 1147064320,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_1.tar": {
      "num_bytes": 1057300480,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_2.tar": {
      "num_bytes": 943237120,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_3.tar": {
      "num_bytes": 837079040,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_4.tar": {
      "num_bytes": 1055385600,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/other/th_other_5.tar": {
      "num_bytes": 176015360,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/invalidated/th_invalidated_0.tar": {
      "num_bytes": 287416320,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/validated/th_validated_0.tar": {
      "num_bytes": 1191843840,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/validated/th_validated_1.tar": {
      "num_bytes": 1079930880,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/validated/th_validated_2.tar": {
      "num_bytes": 1014691840,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/audio/th/validated/th_validated_3.tar": {
      "num_bytes": 744366080,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/train.tsv": {
      "num_bytes": 11337047,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/dev.tsv": {
      "num_bytes": 3803758,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/test.tsv": {
      "num_bytes": 3702050,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/other.tsv": {
      "num_bytes": 71870764,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/invalidated.tsv": {
      "num_bytes": 3301372,
      "checksum": null
    },
    "https://huggingface.co/datasets/mozilla-foundation/common_voice_17_0/resolve/main/transcript/th/validated.tsv": {
      "num_bytes": 50649618,
      "checksum": null
    }
  },
  "download_size": 11176346740,
  "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": 11448184149,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 21220759,
      "num_examples": 32823,
      "dataset_name": "common_voice_17_0"
    },
    "validation": {
      "name": "validation",
      "num_bytes": 7084499,
      "num_examples": 11042,
      "dataset_name": "common_voice_17_0"
    },
    "test": {
      "name": "test",
      "num_bytes": 7004874,
      "num_examples": 11042,
      "dataset_name": "common_voice_17_0"
    },
    "other": {
      "name": "other",
      "num_bytes": 134183952,
      "num_examples": 206935,
      "dataset_name": "common_voice_17_0"
    },
    "invalidated": {
      "name": "invalidated",
      "num_bytes": 6202988,
      "num_examples": 9267,
      "dataset_name": "common_voice_17_0"
    },
    "validated": {
      "name": "validated",
      "num_bytes": 96140337,
      "num_examples": 147160,
      "dataset_name": "common_voice_17_0"
    }
  },
  "version": {
    "version_str": "17.0.0",
    "major": 17,
    "minor": 0,
    "patch": 0
  }
}