| This week we will walk through the components used in the transcription service along with how they are integrated and deployed. This has been updated over the year to incorporate new features and infrastructure as it became available.
This session will be a little light on AI, but should give you an idea of what is involved in making a product that is consumable by the general public. There is likely too much to cover in an hour, so we’ll start with the basic framework and dive in wherever folks want. Also – if you join us for the meetup, I’ll share the code behind all of this.
Basic Technologies:
- Docker – separate containers for UI and transcription service
- Faster Whisper – does the transcription
- Paragraph Detection – finds the best breaks
- Summarization – does it hallucinate, you bet!
- Flask – web server behind the UI
- React – Typescript based UI
- SocketIO – live updates between web server and UI
- Pytest – making sure stuff works
- Terraform – couldn’t do AWS without this
- Stripe – how to get paid
Amazon Web Service Components:
- AWS Container Registry
- AWS CloudWatch
- AWS Lambda
- AWS S3
- AWS Fargate
- AWS SQS
- AWS SES
- AWS DynamoDB
- AWS AIM
Also – the recordings for the last two sessions are now posted at https://hsv.ai/videos/ |
