63. How to automate transcripts with Amazon Transcribe and OpenAI Whisper
AWS Bites
We built a Step Function that allows us to generate high-quality transcripts for AWS Bites podcast! After evaluating different approaches and technologies we ended up using Amazon transcribe and OpenAI whisper. They both have their pros and cons but combined together they gave us everything we were looking for with quite a good degree of accuracy! In this episode, we describe our use case, our research, and how eventually we did go about productionizing our final solution.
If you run a podcast and you would like to do something similar, we have open source our solution. It's called PodWhisperer and you can find it on GitHub: https://github.com/fourTheorem/podwhisperer .
💰 SPONSORS 💰
AWS Bites is sponsored by fourTheorem (https://fourtheorem.com/). fourTheorem is an AWS Consulting Partner offering training, cloud migration, and modern application architecture.
🔖 Chapters:
00:00 Intro 01:07 Why do we need transcripts? 02:36 How can you generate transcripts for a podcast? 05:20 The pros and cons of Amazon Transcribe 06:57 Looking at OpenAI Whisper 08:20 Combining OpenAI Whisper and Amazon Transcribe using Step Functions 12:30 How to increase the quality of the final transcription 13:32 How we integrated the transcripts into awsbites.com 14:50 What's automated and what's still manual? 16:03 Podwhisperer, our open-source solution for automated podcast transcriptions 17:35 Closing notes
In this episode, we mentioned the following resources:
- PodWhisperer on GitHub: https://github.com/fourTheorem/podwhisperer/
- Amazon Transcribe https://aws.amazon.com/transcribe
- OpenAI Whisper announcement blog post: https://openai.com/blog/whisper/
You can listen to AWS Bites wherever you get your podcasts:
- Apple Podcasts: https://podcasts.apple.com/us/podcast/aws-bites/id1585489017
- Spotify: https://open.spotify.com/show/3Lh7PzqBFV6yt5WsTAmO5q
- Google: https://podcasts.google.com/feed/aHR0cHM6Ly9hbmNob3IuZm0vcy82YTMzMTJhMC9wb2RjYXN0L3Jzcw==
- Breaker: https://www.breaker.audio/aws-bites
- RSS: ​​https://anchor.fm/s/6a3312a0/podcast/rss
Do you have any AWS questions you would like us to address? Leave a comment here or connect with us on Twitter:
#AWS #speechtotext #openai ... https://www.youtube.com/watch?v=OV9uNQHZpJ4
109397729 Bytes