AWS CDK で文字起こし + 翻訳パイプラインを作ってみた /jawsug-bgnr-26-lt

AWS CDK で文字起こし + 翻訳パイプラインを作ってみた /jawsug-bgnr-26-lt

JAWS-UG 初心者支部 #26 の LT スライドです。#24 で宿題となっていた Amazon Transcribe と Amazon Translate、および Amazon S3 と AWS Lambda を用いた文字起こし + 翻訳パイプラインの作成を、 AWS CDK でやってみた という内容です。

573d75e1a72107ff5c806d7e70a9e67d?s=128

YoshihiroITO

April 28, 2020
Tweet

Transcript

  1.  ҏ౻Յ༸:PTIJIJSP*UP "84$%,Ͱ จࣈى͜͠ ຋༁ύΠϓϥΠϯΛ ࡞ͬͯΈͨ <+"846(ॳ৺ऀࢧ෦> KBXTVH@CHOSKBXTVHDIJCB

  2. ॴଐɾ୲౰ ɹɹגࣜձࣾϞϦαϫ ɹɹΠϯϑϥɾαʔόαΠυ ޷͖ͳ"84ͷαʔϏε ɹɹ"84-BNCEB ɹɹ"84$FSUJGJDBUF.BOBHFS झຯ ɹɹεϐʔυΩϡʔϒ ɹɹಓͷӺΊ͙Γ ϒϩά

    ɹɹIUUQTNJDIJNBOJOFU ࣗݾ঺հ ҏ౻Յ༸:PTIJIJSP*UP ɹɹ!NJDIJNBOJ
  3. ॓୊ͷ಺༰Λ͓͞Β͍ "84$%,ͱ͸ "84$%,Ͱ॓୊΍ͬͯΈͨ ·ͱΊ ˞࿩͞ͳ͍͜ͱ "84$%,ͷৄࡉͳઆ໌ -BNCEBؔ਺ͷ࣮૷಺༰ͷৄࡉ ΞδΣϯμ

  4. ॓୊ͷ಺༰Λ͓͞Β͍

  5. ॓୊ͷ಺༰Λ͓͞Β͍

  6. ॓୊ͷ಺༰Λ͓͞Β͍

  7. "84$%,ͱ͸ IUUQTEPDTBXTBNB[PODPNDELMBUFTUHVJEFIPNFIUNM

  8. "84$%,ͱ͸ IUUQTEPDTBXTBNB[PODPNDELMBUFTUHVJEFIPNFIUNM ͬ͘͟Γ຋༁͢Δͱɺ"84$%,͸ $MPVE'PSNBUJPOΛհͯ͠"84ͷϦιʔεΛ؅ཧ͢ΔͨΊͷϑϨʔϜϫʔΫ

  9. "84$%,ͱ͸ ͭ·ΓɺͲ͏͍͏͜ͱʁ

  10. "84$%,ͱ͸ ͭ·ΓɺͲ͏͍͏͜ͱʁ  "84ͷϦιʔεΛओཁͳݴޠͰɺϓϩάϥϜΛॻ͘Α͏ʹఆٛͰ͖Δ 5ZQF4DSJQU 1ZUIPOͳͲ   ϓϩάϥϜΛ΋ͱʹͯ͠$MPVE'PSNBUJPOςϯϓϨʔτΛੜ੒Ͱ͖Δ 

    DELίϚϯυͰςϯϓϨʔτͷ࣮ߦ·ͰՄೳ
  11. "84$%,Ͱ॓୊΍ͬͯΈͨ

  12. "84$%,Ͱ॓୊΍ͬͯΈͨ -BNCEBؔ਺ͷ࡞੒  จࣈى͜͠ॲཧ༻transcribe.py ϋϯζΦϯΛ΄΅ͦͷ··   ຋༁ॲཧ༻translate_from_transcribe.py

  13. "84$%,Ͱ॓୊΍ͬͯΈͨ ֤Ϧιʔεͷఆٛ  4όέοτY  -BNCEBؔ਺Y  *".ϩʔϧɺ*".ϙϦγʔ  4Πϕϯτιʔε

    ˞$%,ͷϓϩάϥϜ͸5ZQF4DSJQUͰॻ͍͍͖ͯ·͢
  14. "84$%,Ͱ॓୊΍ͬͯΈͨ ֤Ϧιʔεͷఆٛ  4όέοτY  -BNCEBؔ਺Y  *".ϩʔϧɺ*".ϙϦγʔ  4Πϕϯτιʔε

    ˞$%,ͷϓϩάϥϜ͸5ZQF4DSJQUͰॻ͍͍͖ͯ·͢
  15. "84$%,Ͱ॓୊΍ͬͯΈͨ 4όέοτͷఆٛ

  16. "84$%,Ͱ॓୊΍ͬͯΈͨ 4όέοτͷఆٛ ͦΕͧΕͷ4όέοτ໊Λ ഑ྻͰఆٛ

  17. "84$%,Ͱ॓୊΍ͬͯΈͨ 4όέοτͷఆٛ ͦΕͧΕͷ4όέοτ໊Λ ഑ྻͰఆٛ GPS&BDI Ͱ 4όέοτΛఆٛ

  18. "84$%,Ͱ॓୊΍ͬͯΈͨ -BNCEBؔ਺ͷఆٛ

  19. "84$%,Ͱ॓୊΍ͬͯΈͨ -BNCEBؔ਺ͷఆٛ -BNCEBؔ਺ ຊମͷఆٛ

  20. "84$%,Ͱ॓୊΍ͬͯΈͨ -BNCEBؔ਺ͷఆٛ *".ϩʔϧΛ௥Ճ -BNCEBؔ਺ ຊମͷఆٛ

  21. "84$%,Ͱ॓୊΍ͬͯΈͨ -BNCEBؔ਺ͷఆٛ *".ϩʔϧΛ௥Ճ ΠϕϯτιʔεΛ௥Ճ -BNCEBؔ਺ ຊମͷఆٛ

  22. "84$%,Ͱ॓୊΍ͬͯΈͨ $MPVE'PSNBUJPOςϯϓϨʔτੜ੒

  23. "84$%,Ͱ॓୊΍ͬͯΈͨ $MPVE'PSNBUJPOςϯϓϨʔτੜ੒

  24. "84$%,Ͱ॓୊΍ͬͯΈͨ $MPVE'PSNBUJPOςϯϓϨʔτੜ੒

  25. "84$%,Ͱ॓୊΍ͬͯΈͨ σϓϩΠ

  26. "84$%,Ͱ॓୊΍ͬͯΈͨ σϓϩΠ

  27. "84$%,Ͱ॓୊΍ͬͯΈͨ σϓϩΠ

  28. "84$%,Ͱ॓୊΍ͬͯΈͨ σϓϩΠ

  29. "84$%,Ͱ॓୊΍ͬͯΈͨ σϓϩΠ

  30. "84$%,Ͱ॓୊΍ͬͯΈͨ σϓϩΠ 111111111111

  31. "84$%,Ͱ॓୊΍ͬͯΈͨ ಈ࡞֬ೝ

  32. "84$%,Ͱ॓୊΍ͬͯΈͨ ಈ࡞֬ೝ )FMMP%PZPV TQFBLBGPSFJHO MBOHVBHF 0OFMBOHVBHF JTOFWFSFOPVHI

  33. "84$%,Ͱ॓୊΍ͬͯΈͨ ಈ࡞֬ೝ )FMMP%PZPV TQFBLBGPSFJHO MBOHVBHF 0OFMBOHVBHF JTOFWFSFOPVHI ❯ aws s3

    cp sample.mp3 s3://transcribe-input-bucket upload: sample.mp3 to s3://transcribe-input-bucket/sample.mp3
  34. "84$%,Ͱ॓୊΍ͬͯΈͨ ಈ࡞֬ೝ )FMMP%PZPV TQFBLBGPSFJHO MBOHVBHF 0OFMBOHVBHF JTOFWFSFOPVHI ❯ aws s3

    cp sample.mp3 s3://transcribe-input-bucket upload: sample.mp3 to s3://transcribe-input-bucket/sample.mp3 ͠͹Β͘͢Δͱʜ
  35. "84$%,Ͱ॓୊΍ͬͯΈͨ ಈ࡞֬ೝ )FMMP%PZPV TQFBLBGPSFJHO MBOHVBHF 0OFMBOHVBHF JTOFWFSFOPVHI ❯ aws s3

    cp sample.mp3 s3://transcribe-input-bucket upload: sample.mp3 to s3://transcribe-input-bucket/sample.mp3 ͠͹Β͘͢Δͱʜ
  36. ·ͱΊ  "NB[PO4͸ͨͩͷετϨʔδͰ͸ͳ͍  αʔόϨεָ͍͠  "84$%,ָ͍͠ ˙ϒϩάهࣄ +"846(ॳ৺ऀࢧ෦αʔόϨεϋϯζΦϯษڧձͷ॓୊Λ΍ͬͯΈͨKBXTVH@CHOSKBXTVH IUUQTNJDIJNBOJOFUQPTUBXTKBXTVHCHOSTFSWFSMFTTRVJLDIBOETPO

    ˙$%,ϓϩδΣΫτͷιʔείʔυ IUUQTHJUIVCDPNNJDIJNBOJKBXTVHCHOSIPNFXPSL
  37. ͓͠·͍ KBXTVH@CHOSKBXTVHDIJCB