{
  "builder_name": "parquet",
  "citation": "",
  "config_name": "default",
  "dataset_name": "multitask-national-speech-corpus-v1",
  "dataset_size": 571224336,
  "description": "",
  "download_checksums": {
    "hf://datasets/MERaLiON/Multitask-National-Speech-Corpus-v1@d169debbce4a2dc07f7293360d3eed33c06793b9/ASR-PART1-Test/train-00000-of-00002.parquet": {
      "num_bytes": 269417015,
      "checksum": null
    },
    "hf://datasets/MERaLiON/Multitask-National-Speech-Corpus-v1@d169debbce4a2dc07f7293360d3eed33c06793b9/ASR-PART1-Test/train-00001-of-00002.parquet": {
      "num_bytes": 290433823,
      "checksum": null
    }
  },
  "download_size": 559850838,
  "features": {
    "context": {
      "sampling_rate": 16000,
      "_type": "Audio"
    },
    "instruction": {
      "dtype": "string",
      "_type": "Value"
    },
    "answer": {
      "dtype": "string",
      "_type": "Value"
    }
  },
  "homepage": "",
  "license": "",
  "size_in_bytes": 1131075174,
  "splits": {
    "train": {
      "name": "train",
      "num_bytes": 571224336,
      "num_examples": 3000,
      "shard_lengths": [
        2700,
        300
      ],
      "dataset_name": "multitask-national-speech-corpus-v1"
    }
  },
  "version": {
    "version_str": "0.0.0",
    "major": 0,
    "minor": 0,
    "patch": 0
  }
}