SWISSAI DATA as of 2026-07-22 14:14

#775

/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech
kindshar
statusactive
samples14,621,415
counted viashar cuts
size1.5 GB
files7,441
first seen2026-07-22 14:09
last seen2026-07-22 14:09
registered2026-07-22 14:09

samples

#idstartdurationchannelsupervisionsrecordingcustomtype
1
X0000016288_124567481_S00192
0
1.87
0
[
  {
    "id": "X0000016288_124567481_S00192",
    "recording_id": "X0000016288_124567481_S00192",
    "start": 0.0,
    "duration": 1.87,
    "channel": 0,
    "text": "\u4ed6\u4eec\u5176\u5b9e\u662f\u975e\u5e38\u77ed\u7684\u4e00\u4e2a\u65f6\u95f4",
    "language": "Chinese"
  }
]
{
  "id": "X0000016288_124567481_S00192",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 44880,
  "duration": 1.87,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    17328,
    19358,
    2499,
    76667,
    93671,
    2713,
    26535,
    23982
  ],
  "rms_db": -19.96,
  "source_id": "X0000016288_124567481",
  "clip_num": 118,
  "clip_start": 0.0
}
MonoCut
2
X0000016294_101897678_S00156
0
1.24
0
[
  {
    "id": "X0000016294_101897678_S00156",
    "recording_id": "X0000016294_101897678_S00156",
    "start": 0.0,
    "duration": 1.24,
    "channel": 0,
    "text": "\u5c31\u662f\u524d\u4e00\u9635\u6211\u770b\u770b\u5230",
    "language": "Chinese"
  }
]
{
  "id": "X0000016294_101897678_S00156",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 29760,
  "duration": 1.24,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    10459,
    6141,
    3087,
    11305,
    1181,
    85360,
    59130
  ],
  "rms_db": -19.67,
  "source_id": "X0000016294_101897678",
  "clip_num": 118,
  "clip_start": 0.0
}
MonoCut
3
X0000016301_211565281_S00919
0
3.41
0
[
  {
    "id": "X0000016301_211565281_S00919",
    "recording_id": "X0000016301_211565281_S00919",
    "start": 0.0,
    "duration": 3.41,
    "channel": 0,
    "text": "\u4ed6\u4eec\u5927\u7684\u751f\u610f\u8fd8\u662f\u5728\u8fd9\u4e2a\u7535\u89c6\u7f51\u7edc\u4e0a",
    "language": "Chinese"
  }
]
{
  "id": "X0000016301_211565281_S00919",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 81840,
  "duration": 3.41,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    17328,
    5368,
    2713,
    7360,
    9344,
    68874,
    44929,
    55675,
    80827,
    57644,
    6046,
    1156,
    4445
  ],
  "rms_db": -18.63,
  "source_id": "X0000016301_211565281",
  "clip_num": 560,
  "clip_start": 0.0
}
MonoCut
4
X0000016296_135343932_S00019
0
2.12
0
[
  {
    "id": "X0000016296_135343932_S00019",
    "recording_id": "X0000016296_135343932_S00019",
    "start": 0.0,
    "duration": 2.12,
    "channel": 0,
    "text": "\u6ca1\u6709\u8ddf\u5927\u5bb6\u8bf4\u662f\u5728\u505a\u4ec0\u4e48",
    "language": "Chinese"
  }
]
{
  "id": "X0000016296_135343932_S00019",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 50880,
  "duration": 2.12,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    16685,
    17368,
    1159,
    105024,
    2827,
    123254,
    38388,
    10494
  ],
  "rms_db": -18.69,
  "source_id": "X0000016296_135343932",
  "clip_num": 16,
  "clip_start": 0.0
}
MonoCut
5
X0000016290_94976484_S00541
0
0.92
0
[
  {
    "id": "X0000016290_94976484_S00541",
    "recording_id": "X0000016290_94976484_S00541",
    "start": 0.0,
    "duration": 0.92,
    "channel": 0,
    "text": "\u5728\u90a3\u4e2a\u5e74\u4ee3",
    "language": "Chinese"
  }
]
{
  "id": "X0000016290_94976484_S00541",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 22080,
  "duration": 0.92,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    35870,
    6973,
    12326
  ],
  "rms_db": -14.55,
  "source_id": "X0000016290_94976484",
  "clip_num": 375,
  "clip_start": 0.0
}
MonoCut
6
X0000016287_92761015_S00040
0
1.61
0
[
  {
    "id": "X0000016287_92761015_S00040",
    "recording_id": "X0000016287_92761015_S00040",
    "start": 0.0,
    "duration": 1.61,
    "channel": 0,
    "text": "\u5927\u5bb6\u5f88\u5f00\u6e90\u5206\u4eab",
    "language": "Chinese"
  }
]
{
  "id": "X0000016287_92761015_S00040",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 38640,
  "duration": 1.61,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    105024,
    13440,
    19621,
    41388,
    5020,
    65373
  ],
  "rms_db": -17.39,
  "source_id": "X0000016287_92761015",
  "clip_num": 28,
  "clip_start": 0.0
}
MonoCut
7
X0000016293_85338323_S00143
0
1.54
0
[
  {
    "id": "X0000016293_85338323_S00143",
    "recording_id": "X0000016293_85338323_S00143",
    "start": 0.0,
    "duration": 1.54,
    "channel": 0,
    "text": "\u5443\u5f53\u65f6\u7e41\u534e\u65f6\u4ee3\u7684",
    "language": "Chinese"
  }
]
{
  "id": "X0000016293_85338323_S00143",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 36960,
  "duration": 1.54,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    42549,
    25762,
    49235,
    1129,
    34245,
    78284,
    2713
  ],
  "rms_db": -23.35,
  "source_id": "X0000016293_85338323",
  "clip_num": 99,
  "clip_start": 0.0
}
MonoCut
8
X0000016300_100357723_S00144
0
2.28
0
[
  {
    "id": "X0000016300_100357723_S00144",
    "recording_id": "X0000016300_100357723_S00144",
    "start": 0.0,
    "duration": 2.28,
    "channel": 0,
    "text": "\u5b83\u7684\u8fd9\u4e2a\u505a\u51b3\u7b56\u5c42\u9762\u4e0a\u554a",
    "language": "Chinese"
  }
]
{
  "id": "X0000016300_100357723_S00144",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 54720,
  "duration": 2.28,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    29497,
    2713,
    19853,
    38388,
    41561,
    70323,
    8057,
    1130,
    8682,
    4445,
    9141
  ],
  "rms_db": -24.23,
  "source_id": "X0000016300_100357723",
  "clip_num": 109,
  "clip_start": 0.0
}
MonoCut
9
X0000016301_211565281_S00752
0
1.28
0
[
  {
    "id": "X0000016301_211565281_S00752",
    "recording_id": "X0000016301_211565281_S00752",
    "start": 0.0,
    "duration": 1.28,
    "channel": 0,
    "text": "\u5c31\u662f\u8bf4\u89c9\u5f97\u8fd8\u662f\u6709\u673a\u4f1a\u5566",
    "language": "Chinese"
  }
]
{
  "id": "X0000016301_211565281_S00752",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 30720,
  "duration": 1.28,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    16836,
    48846,
    68874,
    4673,
    45628,
    9788,
    53238
  ],
  "rms_db": -21.43,
  "source_id": "X0000016301_211565281",
  "clip_num": 443,
  "clip_start": 0.0
}
MonoCut
10
X0000016300_100357723_S00361
0
2.32
0
[
  {
    "id": "X0000016300_100357723_S00361",
    "recording_id": "X0000016300_100357723_S00361",
    "start": 0.0,
    "duration": 2.32,
    "channel": 0,
    "text": "\u4f60\u80af\u5b9a\u9009\u4e00\u4e2a\u5e02\u573a\u60c5\u7eea\u6700\u9ad8\u6da8\u7684\u65f6\u5019\u561b",
    "language": "Chinese"
  }
]
{
  "id": "X0000016300_100357723_S00361",
  "sources": [
    {
      "type": "shar",
      "channels": [
        0
      ],
      "source": ""
    }
  ],
  "sampling_rate": 24000,
  "num_samples": 55680,
  "duration": 2.32,
  "channel_ids": [
    0
  ]
}
{
  "shard_origin": "/capstor/store/cscs/swissai/infra01/audio-datasets/SHAR/stage_2/wenetspeech/cuts.000000.jsonl.gz",
  "shar_epoch": 0,
  "text_tokens": [
    7543,
    79769,
    42850,
    26535,
    18996,
    50381,
    14373,
    6046,
    1170,
    59718,
    27371,
    1168,
    54293,
    35424,
    1155
  ],
  "rms_db": -19.55,
  "source_id": "X0000016300_100357723",
  "clip_num": 257,
  "clip_start": 0.0
}
MonoCut