"Seamless Communication" from Meta AI research is a big deal: really impressive speech-to-speech (and text-to-speech/speech-to-text/text-to-text) language translation models, released today
The main model file is 9GB - I wrote some more notes here: https://simonwillison.net/2023/Dec/1/seamless-communication/
Their interactive demo at https://ai.meta.com/research/seamless-communication/ is very neat - you record a video through your webcam and it plays it back to you translated into a language you select
Simon Willison /
npub13v…4w5eu
2023-12-01 17:24:03
Author Public Key
npub13v97j0kknscwnf5pt87nsn7cxzxwfwl3dsu7ss8qsq7ukmqgwg8q84w5euPublished at
2023-12-01 17:24:03Event JSON
{
"id": "38724e40e2f3999c885a02c016e7986dd9f522f6fcd577be6678188ff9260830",
"pubkey": "8b0be93ed69c30e9a68159fd384fd8308ce4bbf16c39e840e0803dcb6c08720e",
"created_at": 1701451443,
"kind": 1,
"tags": [
[
"proxy",
"https://fedi.simonwillison.net/users/simon/statuses/111506321790027843",
"activitypub"
]
],
"content": "\"Seamless Communication\" from Meta AI research is a big deal: really impressive speech-to-speech (and text-to-speech/speech-to-text/text-to-text) language translation models, released today\n\nThe main model file is 9GB - I wrote some more notes here: https://simonwillison.net/2023/Dec/1/seamless-communication/\n\nTheir interactive demo at https://ai.meta.com/research/seamless-communication/ is very neat - you record a video through your webcam and it plays it back to you translated into a language you select\n\nhttps://cdn.masto.host/fedisimonwillisonnet/media_attachments/files/111/506/312/881/845/536/original/85af112a4222e80c.mp4",
"sig": "38e9c8ae47c228bacb9167fb4b42453db97bd52ea5c022489b81530c573e1194ee05ba02f97f0a3f431fc447e4b60646a6850acb9bdff0a8e86502753384f079"
}