🐦 Twitter Post Details

Viewing enriched Twitter post

@vanstriendaniel

It's raining OCR models again! @Baidu_Inc's Unlimited-OCR is one of the more interesting. You can try it without much effort via a throwaway GPU endpoint on @huggingface Jobs (which recently added port forwarding support) with one command It's OpenAI-compatible, your HF token is the API key, and --timeout makes it self-destruct so you can't leave a GPU running by accident Once it's warm, it's quick and @sgl_project batches concurrent requests, so an agent can boot the model, fire a big async batch at it (say, a whole bucket of newspaper scans), then cancel it. I pointed it at the front page of a 1901 newspaper, "The Commoner" + 6 PDF pages in a single request: tables came back as HTML, equations as LaTeX, figures with captions, reading order preserved across pages. Docs here: https://t.co/mApuKalqSN

Media 1
Media 2
Media 3
Media 4

📊 Media Metadata

{
  "media": [
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069403564892397735/media_0.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069403564892397735/media_0.jpg",
      "type": "photo",
      "filename": "media_0.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069403564892397735/media_1.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069403564892397735/media_1.jpg",
      "type": "photo",
      "filename": "media_1.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069403564892397735/media_2.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069403564892397735/media_2.jpg",
      "type": "photo",
      "filename": "media_2.jpg"
    },
    {
      "url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069403564892397735/media_3.jpg",
      "media_url": "https://crmoxkoizveukayfjuyo.supabase.co/storage/v1/object/public/media/posts/2069403564892397735/media_3.jpg",
      "type": "photo",
      "filename": "media_3.jpg"
    }
  ],
  "processed_at": "2026-06-23T15:33:24.810991",
  "pipeline_version": "2.0"
}

🔧 Raw API Response

{
  "type": "tweet",
  "id": "2069403564892397735",
  "url": "https://x.com/vanstriendaniel/status/2069403564892397735",
  "twitterUrl": "https://twitter.com/vanstriendaniel/status/2069403564892397735",
  "text": "It's raining OCR models again! \n\n@Baidu_Inc's Unlimited-OCR is one of the more interesting. You can try it without much effort via a throwaway GPU endpoint on @huggingface Jobs  (which recently added port forwarding support) with one command \n\nIt's OpenAI-compatible, your HF token is the API key, and --timeout makes it self-destruct so you can't leave a GPU running by accident \n\nOnce it's warm, it's quick and @sgl_project batches concurrent requests, so an agent can boot the model, fire a big async batch at it (say, a whole bucket of newspaper scans), then cancel it.\n\nI pointed it at the front page of a 1901 newspaper, \"The Commoner\" + 6 PDF pages in a single request: tables came back as HTML, equations as LaTeX, figures with captions, reading order preserved across pages.\n\nDocs here: \nhttps://t.co/mApuKalqSN",
  "source": "Twitter for iPhone",
  "retweetCount": 10,
  "replyCount": 1,
  "likeCount": 70,
  "quoteCount": 0,
  "viewCount": 4143,
  "createdAt": "Tue Jun 23 12:53:52 +0000 2026",
  "lang": "en",
  "bookmarkCount": 54,
  "isReply": false,
  "inReplyToId": null,
  "conversationId": "2069403564892397735",
  "displayTextRange": [
    0,
    275
  ],
  "inReplyToUserId": null,
  "inReplyToUsername": null,
  "author": {
    "type": "user",
    "userName": "vanstriendaniel",
    "url": "https://x.com/vanstriendaniel",
    "twitterUrl": "https://twitter.com/vanstriendaniel",
    "id": "2828117077",
    "name": "Daniel van Strien",
    "isVerified": false,
    "isBlueVerified": true,
    "verifiedType": null,
    "profilePicture": "https://pbs.twimg.com/profile_images/1274680904217251840/N_svCCtg_normal.jpg",
    "coverPicture": "https://pbs.twimg.com/profile_banners/2828117077/1655807268",
    "description": "",
    "location": "Scotland",
    "followers": 5745,
    "following": 1527,
    "status": "",
    "canDm": false,
    "canMediaTag": false,
    "createdAt": "Tue Sep 23 13:43:54 +0000 2014",
    "entities": {
      "description": {
        "urls": []
      },
      "url": {}
    },
    "fastFollowersCount": 0,
    "favouritesCount": 8084,
    "hasCustomTimelines": true,
    "isTranslator": false,
    "mediaCount": 770,
    "statusesCount": 4843,
    "withheldInCountries": [],
    "affiliatesHighlightedLabel": {},
    "possiblySensitive": false,
    "pinnedTweetIds": [
      "1859606350453440888"
    ],
    "profile_bio": {
      "description": "Machine Learning Librarian @huggingface 🤗 \nI like datasets.",
      "entities": {
        "description": {
          "user_mentions": [
            {
              "id_str": "",
              "indices": [
                27,
                39
              ],
              "name": "",
              "screen_name": "huggingface"
            }
          ]
        },
        "url": {
          "urls": [
            {
              "display_url": "danielvanstrien.xyz",
              "expanded_url": "https://danielvanstrien.xyz/",
              "indices": [
                0,
                23
              ],
              "url": "https://t.co/FnYe1w0XzI"
            }
          ]
        }
      }
    },
    "isAutomated": false,
    "automatedBy": null
  },
  "extendedEntities": {
    "media": [
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/hC35gBLdKX",
        "expanded_url": "https://twitter.com/vanstriendaniel/status/2069403564892397735/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2069401795193929729",
        "indices": [
          276,
          299
        ],
        "media_key": "3_2069401795193929729",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy3/ff0FwABCgACHLf/k/5WoKcAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHLf99/QXAAEKAAIct/+T/lagpwAA",
            "media_key": "3_2069401795193929729"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HLf99_QXAAEapMk.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 634,
              "w": 1132,
              "x": 455,
              "y": 0
            },
            {
              "h": 634,
              "w": 634,
              "x": 704,
              "y": 0
            },
            {
              "h": 634,
              "w": 556,
              "x": 743,
              "y": 0
            },
            {
              "h": 634,
              "w": 317,
              "x": 863,
              "y": 0
            },
            {
              "h": 634,
              "w": 1946,
              "x": 0,
              "y": 0
            }
          ],
          "height": 634,
          "width": 1946
        },
        "sizes": {
          "large": {
            "h": 634,
            "w": 1946
          }
        },
        "type": "photo",
        "url": "https://t.co/hC35gBLdKX"
      },
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/hC35gBLdKX",
        "expanded_url": "https://twitter.com/vanstriendaniel/status/2069403564892397735/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": [
              {
                "h": 70,
                "w": 70,
                "x": 367,
                "y": 847
              },
              {
                "h": 101,
                "w": 101,
                "x": 234,
                "y": 1476
              }
            ]
          },
          "orig": {
            "faces": [
              {
                "h": 70,
                "w": 70,
                "x": 367,
                "y": 847
              },
              {
                "h": 101,
                "w": 101,
                "x": 234,
                "y": 1476
              }
            ]
          }
        },
        "id_str": "2069403137467645952",
        "indices": [
          276,
          299
        ],
        "media_key": "3_2069403137467645952",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy3/zB51oAACgACHLf/k/5WoKcAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHLf/MHnWgAAKAAIct/+T/lagpwAA",
            "media_key": "3_2069403137467645952"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HLf_MHnWgAA8XHu.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 773,
              "w": 1380,
              "x": 0,
              "y": 0
            },
            {
              "h": 1380,
              "w": 1380,
              "x": 0,
              "y": 0
            },
            {
              "h": 1573,
              "w": 1380,
              "x": 0,
              "y": 0
            },
            {
              "h": 2000,
              "w": 1000,
              "x": 380,
              "y": 0
            },
            {
              "h": 2000,
              "w": 1380,
              "x": 0,
              "y": 0
            }
          ],
          "height": 2000,
          "width": 1380
        },
        "sizes": {
          "large": {
            "h": 2000,
            "w": 1380
          }
        },
        "type": "photo",
        "url": "https://t.co/hC35gBLdKX"
      },
      {
        "allow_download_status": {
          "allow_download": true
        },
        "display_url": "pic.twitter.com/hC35gBLdKX",
        "expanded_url": "https://twitter.com/vanstriendaniel/status/2069403564892397735/photo/1",
        "ext_master_playlist_only": [],
        "ext_media_availability": {
          "status": "Available"
        },
        "ext_playlists": [],
        "features": {
          "large": {
            "faces": []
          },
          "orig": {
            "faces": []
          }
        },
        "id_str": "2069403255692476416",
        "indices": [
          276,
          299
        ],
        "media_key": "3_2069403255692476416",
        "media_results": {
          "id": "QXBpTWVkaWFSZXN1bHRzOgwAAQoAARy3/0wAlkAACgACHLf/k/5WoKcAAA==",
          "result": {
            "__typename": "ApiMedia",
            "id": "QXBpTWVkaWE6DAABCgABHLf/TACWQAAKAAIct/+T/lagpwAA",
            "media_key": "3_2069403255692476416"
          }
        },
        "media_url_https": "https://pbs.twimg.com/media/HLf_TACWQAAN8n7.jpg",
        "original_info": {
          "focus_rects": [
            {
              "h": 641,
              "w": 1145,
              "x": 0,
              "y": 479
            },
            {
              "h": 1145,
              "w": 1145,
              "x": 0,
              "y": 40
            },
            {
              "h": 1185,
              "w": 1039,
              "x": 0,
              "y": 0
            },
            {
              "h": 1185,
              "w": 593,
              "x": 0,
              "y": 0
            },
            {
              "h": 1185,
              "w": 1145,
              "x": 0,
              "y": 0
            }
          ],
          "height": 1185,
          "width": 1145
        },
        "sizes": {
          "large": {
            "h": 1185,
            "w": 1145
          }
        },
        "type": "photo",
        "url": "https://t.co/hC35gBLdKX"
      }
    ]
  },
  "card": null,
  "place": {},
  "entities": {
    "hashtags": [],
    "symbols": [],
    "urls": [
      {
        "display_url": "huggingface.co/datasets/uv-sc…",
        "expanded_url": "https://huggingface.co/datasets/uv-scripts/ocr/blob/main/serving-unlimited-ocr.md#1-start-the-server",
        "indices": [
          797,
          820
        ],
        "url": "https://t.co/mApuKalqSN"
      }
    ],
    "user_mentions": [
      {
        "id_str": "820440736336228352",
        "indices": [
          33,
          43
        ],
        "name": "Baidu Inc.",
        "screen_name": "Baidu_Inc"
      },
      {
        "id_str": "778764142412984320",
        "indices": [
          159,
          171
        ],
        "name": "Hugging Face",
        "screen_name": "huggingface"
      },
      {
        "id_str": "1923440305703092226",
        "indices": [
          413,
          425
        ],
        "name": "SGLang",
        "screen_name": "sgl_project"
      }
    ]
  },
  "quoted_tweet": null,
  "retweeted_tweet": null,
  "isLimitedReply": false,
  "communityInfo": null,
  "article": null
}