News for hackers. Stuff that matters.

A comment on Base64.ai – Extract text, data, photos and more from all types of docs. Parent comment

Re:Base64.ai – Extract text, data, photos and more from all ... by Darkphibre on Wednesday February 10, 2021 @04:22AM (#26087104)
Interesting!

I've been thinking of running OCR on video frames. I'd also like to do speech-to-text extraction for searching my archives later (have about 4TB of video to trawl through, and desire text-based search capabilities). It's an interesting space to explore, but everything's been moving to web-service at a cost-prohibitive model.

[ Parent | on HN ]
Re:Base64.ai – Extract text, data, photos and more from all ... by voiper1 on Wednesday February 10, 2021 @04:48AM (#26087274)
Should be able to use ffmpeg[0] to extract a single frame each second/keyframe (doubtful it's worth doing every single frame) and then pass it to tesseract.

For speech to text.. if english, try mozilla's deepspeech? https://github.com/mozilla/DeepSpeech

Might be fun to try.

[0] https://stackoverflow.com/questions/27568254/how-to-extract-...

[ Parent | on HN ]
Re:Base64.ai – Extract text, data, photos and more from all ... by Darkphibre on Wednesday February 10, 2021 @03:06PM (#26093988)
Yup, was planning to use ffmpeg (or, more likely, OpenCV), and a subset of the frames.

Thanks so much for the tip on DeepSpeech!

[ Parent | on HN ]
Re:Base64.ai – Extract text, data, photos and more from all ... by oebilgen on Wednesday February 10, 2021 @11:42AM (#26091464)
@Darkphibre; we are happy to provide you an AI that takes in a video and outputs OCR and speech-to-text. With Base64.ai, you don't have to worry about the implementation details, and focus on your projects. Let's have a meeting to discuss more? https://base64.ai/meeting
[ Parent | on HN ]
Re:Base64.ai – Extract text, data, photos and more from all ... by ghgr on Wednesday February 10, 2021 @04:50AM (#26087289)
For speech-to-text extraction you can try Silero [1].

Free software (AGPL-3.0 License), fast, highly accurate and extremely simple to deploy (I have no affiliation with them).

[1] https://github.com/snakers4/silero-models

[ Parent | on HN ]
Re:Base64.ai – Extract text, data, photos and more from all ... by Darkphibre on Wednesday February 10, 2021 @03:07PM (#26093993)
Thanks for the heads up! Will definitely check it out.
[ Parent | on HN ]
Re:Base64.ai – Extract text, data, photos and more from all ... by danielmorozoff on Wednesday February 10, 2021 @07:15AM (#26088191)
If you’re looking to index/ process video - maybe we can help. Checkout Vidrovr (https://vidrovr.com)

Full disclosure im one of the founders.

[ Parent | on HN ]