ATProto Browser

ATProto Browser

Experimental browser for the Atmosphere

Post

@mlcommons.org releases Unsupervised People's Speech dataset: 1M+ hours of multilingual audio 821K+ hours of detected speech 89 languages 48+ TB of data Empowering research in: ✅ Speech recognition ✅ Language ID ✅ Global communication tech Learn more: mlcommons.org/2025/01/new-... #nlp #datasets

Jan 30, 2025, 8:40 PM

Record data

{
  "uri": "at://did:plc:uavs3b5de27ki26k5usmqtxz/app.bsky.feed.post/3lgydr3c4rs2e",
  "cid": "bafyreidvgbzgs7pxyl62hahemgmfhkcw5i3m7yglupnhczh2cvsgozzqty",
  "value": {
    "text": "@mlcommons.org releases Unsupervised People's Speech dataset:\n1M+ hours of multilingual audio\n821K+ hours of detected speech\n89 languages\n48+ TB of data\n\nEmpowering research in:\n✅ Speech recognition\n✅ Language ID\n✅ Global communication tech\n\nLearn more: mlcommons.org/2025/01/new-...\n\n#nlp #datasets",
    "$type": "app.bsky.feed.post",
    "embed": {
      "$type": "app.bsky.embed.images",
      "images": [
        {
          "alt": "",
          "image": {
            "$type": "blob",
            "ref": {
              "$link": "bafkreiffi7v44dn7ns56ekew75rc6tlkz7c4ynajq7aqkg5ygklfvt5scq"
            },
            "mimeType": "image/jpeg",
            "size": 537480
          },
          "aspectRatio": {
            "width": 1200,
            "height": 1200
          }
        }
      ]
    },
    "langs": [
      "en"
    ],
    "facets": [
      {
        "$type": "app.bsky.richtext.facet",
        "index": {
          "byteEnd": 14,
          "byteStart": 0
        },
        "features": [
          {
            "did": "did:plc:uavs3b5de27ki26k5usmqtxz",
            "$type": "app.bsky.richtext.facet#mention"
          }
        ]
      },
      {
        "index": {
          "byteEnd": 289,
          "byteStart": 260
        },
        "features": [
          {
            "uri": "https://mlcommons.org/2025/01/new-unsupervised-peoples-speech/",
            "$type": "app.bsky.richtext.facet#link"
          }
        ]
      },
      {
        "index": {
          "byteEnd": 295,
          "byteStart": 291
        },
        "features": [
          {
            "tag": "nlp",
            "$type": "app.bsky.richtext.facet#tag"
          }
        ]
      },
      {
        "index": {
          "byteEnd": 305,
          "byteStart": 296
        },
        "features": [
          {
            "tag": "datasets",
            "$type": "app.bsky.richtext.facet#tag"
          }
        ]
      }
    ],
    "createdAt": "2025-01-30T20:40:00.775Z"
  }
}