[{"data":1,"prerenderedAt":139},["ShallowReactive",2],{"project-25366014":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":29,"sentiment":30,"stance_mix":31,"scored_comments":33,"aspects":34,"strip":36,"post_text":30,"what":37,"said":64,"maker_in_thread":86,"shape":93,"grid":95,"attempts":101,"same_week":102,"maker_shows":131,"maker_hidden":132,"reader_version":133,"card":134},"25366014","cortex","Deploy a translation API for 100+ languages with machine learning","title","Show HN: Deploy a translation API for 100+ languages with machine learning","https:\u002F\u002Fgithub.com\u002Fcortexlabs\u002Fcortex\u002Ftree\u002Ftranslator-example\u002Fexamples\u002Fmodel-caching\u002Fpython\u002Ftranslator","github.com","calebkaiser",1607552109,2020,12,3,2202,3028,73,"shown","ai","machine translation API","api",[24,25,26,27,28],"machine translation","translation api","multi-model caching","cortex deployment","hugging face models","quiet",null,{"positive":32,"neutral":33,"mixed":32,"critical":32},0,1,{"performance":35},{"positive":32,"critical":32},[32,15,32],{"problem":38,"audience":30,"pricing":30,"motivation":30,"time_to_build":30,"stack":45,"openness":62,"stage":63,"team_size":63},{"value":39,"source":40,"evidence":41},"On-demand translation between over 100 languages","maker",[42],{"id":43,"by":11,"text":44},"25366034","Hey HN! This is a small project I've been tinkering with for a while. In simplest terms, it is an open source web service that enables on-demand translation between over 100…",[46,50,54,58],{"value":47,"source":40,"evidence":48},"Cortex (ML deployment)",[49],{"id":43,"by":11,"text":44},{"value":51,"source":40,"evidence":52},"AWS S3",[53],{"id":43,"by":11,"text":44},{"value":55,"source":40,"evidence":56},"AWS EC2",[57],{"id":43,"by":11,"text":44},{"value":59,"source":40,"evidence":60},"Hugging Face translation models from University of Helsinki",[61],{"id":43,"by":11,"text":44},"open_source","unknown",{"praise":65,"objections":74,"requests":75,"questions":80,"alternatives":85},[66],{"value":67,"source":68,"evidence":69},"Looks really cool","commenter",[70],{"id":71,"by":72,"text":73},"25370325","mendeza","Wow, this is really cool! Is inference running on GPU or CPU? I wonder how well this would run if model storage and inference is done on a jetson nano!",[],[76],{"value":77,"source":68,"evidence":78},"Run on a Jetson Nano",[79],{"id":71,"by":72,"text":73},[81],{"value":82,"source":68,"evidence":83},"Does inference run on GPU or CPU",[84],{"id":71,"by":72,"text":73},[],{"comments":87,"answered":33,"key":88},2,[89,90],{"id":43,"text":44},{"id":91,"text":92},"25373734","Thanks! The inference is currently run on GPU (a g4dn.xlarge instance), but can be swapped for CPUs by simply changing the compute request in the configuration YAML. In theory, a…",{"commenters":87,"max_depth":15,"maker_replies":87,"first_comment_mins":87,"lifespan_hours":94},16,[96,98,100],[43,32,32,97,11,33],"project\u002Fpositive\u002Fexecution",[71,32,15,99,72,32],"project\u002Fneutral\u002Fperformance",[91,32,32,99,11,33],[],[103,108,113,118,123,128],{"id":104,"name":105,"points":106,"category":107},"25352385","Web Data Render (WDR)",604,"languages",{"id":109,"name":110,"points":111,"category":112},"25328622","Boltstream",510,"infrastructure",{"id":114,"name":115,"points":116,"category":117},"25361224","Hystoria",375,"productivity",{"id":119,"name":120,"points":121,"category":122},"25365397","Recipe Search",349,"consumer_social",{"id":124,"name":125,"points":126,"category":127},"25355580","Slices",219,"games",{"id":129,"name":130,"points":126,"category":117},"25358108","Typefully",6,false,"v2",{"id":135,"name":5,"line":6,"ai":132,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":30,"top":18,"kw":136,"maker":11,"domain":10,"tier":19,"attempts":32,"strip":137,"url":9,"mix":138,"praise":67,"objection":-1,"sub":21},25366014,[24,25,26,27,28],"030",[32,33,32,32],1794036599409]