Comments (5)
dfw100
commented on September 25, 2024
Hi @yuichiro-honda , could you please provide us with additional information such as steps to reproduce and the AWS resource where you are seeing this error?
from ai-powered-speech-analytics-for-amazon-connect.
yuichiro-honda
commented on September 25, 2024
Hi @dfw100 san.
２つの問いかけにレスポンスありがとうございます。
このサンプルはKVSの45分の制限を超えるために、42分で文字起こしを再実行しているかと思います。
ただし、実際に42分を超えて再実行された時に、その切り替えの20数秒エラーが発生して、
文字起こし結果が欠落します。また、稀に顧客またはオペレータの音声テキスト化が再実行されずに終了します。
推測ですが、再実行時に前のTranscribeの結果が完了していないうちに再実行され、
継続して開始する位置が、Transcribeの結果が完了していない部分より後ろから開始されているのではないかと
思われます。
これは普通に42分以上通話をして、跨ぐ部分で会話をしていれば、毎回再現します。
再現する場合は通話量がもったいないので、42分を5分とかに書き換えて再現したほうがよいです。
from ai-powered-speech-analytics-for-amazon-connect.
angieyu
commented on September 25, 2024
Hi @yuichiro-honda, KVS Session are limited to 45 minutes so we request a new endpoint at 42 minutes and issue a new GetMedia. Please try adjusting the timing in the code.
Please see aws/amazon-kinesis-video-streams-parser-library#108 . We have the same implementation.
Let me know if this answers your question.
from ai-powered-speech-analytics-for-amazon-connect.
yuichiro-honda
commented on September 25, 2024
Hi, @Angela
KVSに45分のリミットがあることは理解しています。
このサンプルはそれが対応されています（42分で再実行）。
ただし、処理に問題があるため、再実行するさいの20数秒の文字起こしが欠落します。
ログにも例外が出力されるはずです。
これは、再実行時に、Transcribeも再実行しているせいかと思われます。
そのため、KVS再実行時にはまだ完了していない文字起こし処理が、中断されてしまうのではないでしょうか？
サンプルプログラムを試せば100％再現するので確認できるかと思います。
42分待つのは長すぎるので、再実行時間を5分程度に変更して試すのがよいかと思います。
ありがとう。
2021年10月12日(火) 6:14 Angela ***@***.***>:
… Hi @yuichiro-honda <https://github.com/yuichiro-honda>, KVS Session are
limited to 45 minutes so we request a new endpoint at 42 minutes and issue
a new GetMedia. Please try adjusting the timing in the code.
Please see aws/amazon-kinesis-video-streams-parser-library#108
<aws/amazon-kinesis-video-streams-parser-library#108>
. We have the same implementation.
Let me know if this answers your question.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
<#32 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/APNBWXRYHLXN6DDBJOX5V3LUGNHUHANCNFSM5FEMWAGA>
.
Triage notifications on the go with GitHub Mobile for iOS
<https://apps.apple.com/app/apple-store/id1477376905?ct=notification-email&mt=8&pt=524675>
or Android
<https://play.google.com/store/apps/details?id=com.github.android&referrer=utm_campaign%3Dnotification-email%26utm_medium%3Demail%26utm_source%3Dgithub>.
--
__________________________________________________
ＡＲアドバンストテクノロジ株式会社【Ａ.Ｒ.Ｉ.】
ユニファイドソリューションユニット
UCネットワーク部 UCサービス第１課
本多 裕一郎（Yuichiro Honda）
<<渋谷オフィス>>
〒150-0002
東京都渋谷区渋谷1-14-16 渋谷野村證券ビル8F
TEL：03-6450-6080 / FAX：03-6450-6088
***@***.***
URL：http://www.ari-jp.com
≪ISMS/ISO27001認証取得≫
≪Ｐマーク認証番号:第17000819号≫
__________________________________________________
from ai-powered-speech-analytics-for-amazon-connect.
kqia040
commented on September 25, 2024
Hey @yuichiro-honda thanks for the update. Here is in the code where this is done
Feel free to update it to see if it suits your use case better. Please keep in mind other API limits if for example if you change it to 5min.
from ai-powered-speech-analytics-for-amazon-connect.
Related Issues (20)
- How can I get Agent Transcript on Front End HOT 2
- How can I get Outgoing Transcript of both agent and customer. HOT 6
- In transcribeStreaming, some languages is not working. HOT 2
- How to get the real time Transcript of both the agent as well as customer? HOT 1
- the maximum session duration for the role HOT 1
- How can I get the real-time agent transcript? HOT 3
- How can i get agent side transciption? Currently I am only able to get customer transcription. HOT 2
- Chat with Translate doesn't work HOT 1
- How to get the real time agent transcript? HOT 4
- How do I add more languages to the translate options? HOT 2
- Chat Translate not working HOT 2
- [Feature] Adding more transcribe language HOT 3
- 同時通話で文字起こしが中断する。 HOT 4
- Chat translate not working HOT 3
- CCP domain changed HOT 1
- How do I remediate RCE 0-day exploit found in Apache Log4j2 HOT 2
- deployment/manifest-generator: No such file or directory HOT 1
- Error on UI when connecting to connect HOT 2
- Build fails with 'manifest-generator: No such file or directory' HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ai-powered-speech-analytics-for-amazon-connect.