Viewing enriched Twitter post
In this clip from his PyTorch Conference Europe 2026 keynote, Patrick von Platen (@MistralAI) discusses why real-world machine interaction requires models that can take continuous input and produce continuous output. Using live transcription as an example, he explains how streaming architectures differ from traditional speech recognition approaches that process larger chunks of audio at once. 🔗 Watch the full keynote: https://t.co/PmM1ak29ay #PyTorchCon
{
"media": [
{
"url": "https://video.twimg.com/amplify_video/2065497078642483200/vid/avc1/720x1280/Pxcz7YdOPE16fDPD.mp4?tag=14",
"type": "video"
}
],
"processed_at": "2026-06-12T18:18:57.933460",
"pipeline_version": "2.0"
}{
"type": "tweet",
"id": "2065497226323914753",
"url": "https://x.com/PyTorch/status/2065497226323914753",
"twitterUrl": "https://twitter.com/PyTorch/status/2065497226323914753",
"text": "In this clip from his PyTorch Conference Europe 2026 keynote, Patrick von Platen (@MistralAI) discusses why real-world machine interaction requires models that can take continuous input and produce continuous output.\n\nUsing live transcription as an example, he explains how streaming architectures differ from traditional speech recognition approaches that process larger chunks of audio at once.\n\n🔗 Watch the full keynote: https://t.co/PmM1ak29ay\n\n#PyTorchCon",
"source": "Twitter for iPhone",
"retweetCount": 1,
"replyCount": 0,
"likeCount": 1,
"quoteCount": 0,
"viewCount": 371,
"createdAt": "Fri Jun 12 18:11:28 +0000 2026",
"lang": "en",
"bookmarkCount": 0,
"isReply": false,
"inReplyToId": null,
"conversationId": "2065497226323914753",
"displayTextRange": [
0,
273
],
"inReplyToUserId": null,
"inReplyToUsername": null,
"author": {
"type": "user",
"userName": "PyTorch",
"url": "https://x.com/PyTorch",
"twitterUrl": "https://twitter.com/PyTorch",
"id": "776585502606721024",
"name": "PyTorch",
"isVerified": false,
"isBlueVerified": true,
"verifiedType": null,
"profilePicture": "https://pbs.twimg.com/profile_images/1813965160702451712/yXV1vRhr_normal.jpg",
"coverPicture": "https://pbs.twimg.com/profile_banners/776585502606721024/1761575044",
"description": "",
"location": "",
"followers": 497032,
"following": 86,
"status": "",
"canDm": false,
"canMediaTag": true,
"createdAt": "Fri Sep 16 00:56:26 +0000 2016",
"entities": {
"description": {
"urls": []
},
"url": {}
},
"fastFollowersCount": 0,
"favouritesCount": 944,
"hasCustomTimelines": true,
"isTranslator": false,
"mediaCount": 1503,
"statusesCount": 3331,
"withheldInCountries": [],
"affiliatesHighlightedLabel": {},
"possiblySensitive": false,
"pinnedTweetIds": [],
"profile_bio": {
"description": "Tensors and neural networks in Python with strong hardware acceleration. PyTorch is an open source project at the Linux Foundation. #PyTorchFoundation",
"entities": {
"description": {
"hashtags": [
{
"indices": [
132,
150
],
"text": "PyTorchFoundation"
}
]
},
"url": {
"urls": [
{
"display_url": "pytorch.org",
"expanded_url": "http://pytorch.org",
"indices": [
0,
23
],
"url": "https://t.co/6SwTBhUwTJ"
}
]
}
}
},
"isAutomated": false,
"automatedBy": null
},
"extendedEntities": {
"media": [
{
"additional_media_info": {
"monetizable": true
},
"display_url": "pic.twitter.com/8RcqsOBKBe",
"expanded_url": "https://twitter.com/PyTorch/status/2065497226323914753/video/1",
"ext_master_playlist_only": [],
"ext_media_availability": {
"status": "Available"
},
"ext_playlists": [],
"id_str": "2065497078642483200",
"indices": [
274,
297
],
"media_key": "13_2065497078642483200",
"media_results": {
"id": "QXBpTWVkaWFSZXN1bHRzOgwABAoAARyqHqZJF6AAAAA=",
"result": {
"__typename": "ApiMedia",
"id": "QXBpTWVkaWE6DAAECgABHKoepkkXoAAAAA==",
"media_key": "13_2065497078642483200"
}
},
"media_url_https": "https://pbs.twimg.com/media/HKoew5rXIAAdVoT.jpg",
"original_info": {
"focus_rects": [],
"height": 1920,
"width": 1080
},
"sizes": {
"large": {
"h": 1920,
"w": 1080
}
},
"type": "video",
"url": "https://t.co/8RcqsOBKBe",
"video_info": {
"aspect_ratio": [
9,
16
],
"duration_millis": 118800,
"variants": [
{
"content_type": "application/x-mpegURL",
"url": "https://video.twimg.com/amplify_video/2065497078642483200/pl/tO7KELORHJEWUvWk.m3u8?tag=14"
},
{
"bitrate": 632000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2065497078642483200/vid/avc1/320x568/k6AHb45zcs_X9cOi.mp4?tag=14"
},
{
"bitrate": 950000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2065497078642483200/vid/avc1/480x852/4zNzaUQe2Jds0LxU.mp4?tag=14"
},
{
"bitrate": 2176000,
"content_type": "video/mp4",
"url": "https://video.twimg.com/amplify_video/2065497078642483200/vid/avc1/720x1280/Pxcz7YdOPE16fDPD.mp4?tag=14"
}
]
}
}
]
},
"card": null,
"place": {},
"entities": {
"hashtags": [
{
"indices": [
449,
460
],
"text": "PyTorchCon"
}
],
"symbols": [],
"timestamps": [],
"urls": [
{
"display_url": "youtu.be/sn5954LcXq8?si…",
"expanded_url": "https://youtu.be/sn5954LcXq8?si=Hf8ABKIZ4-I0cTA2",
"indices": [
424,
447
],
"url": "https://t.co/PmM1ak29ay"
}
],
"user_mentions": [
{
"id_str": "1667249535519805451",
"indices": [
82,
92
],
"name": "Mistral AI",
"screen_name": "MistralAI"
}
]
},
"quoted_tweet": null,
"retweeted_tweet": null,
"isLimitedReply": false,
"communityInfo": null,
"article": null
}