#PDFstories app for audio summaries of pdf files
26 messages · Page 1 of 1 (latest)
Great project!
I would propose, however, that users can select pages to transcribe (provided that the PDF had already been uploaded) if not transcribing from page one of the PDF. So it would be easier for people to read and appreciate particular pages. Also midway there is an error transcribing uploaded content. It should start transcribing the sample PDF content instead of sticking to the uploaded content
Also mp3 summary doesn't work. The contents are just the filename.
And summary as text file brings up only part of the material submitted and transcribed, not everything from the beginning.
Very cool. I just uploaded an archive paper on RL and it did a nice job of summarizing the pages. Is this open source? or are you trying to make a business? what are you using for the text->speech?
Thank you very much for the suggestions and outlining of the issues. I will take a look at them as soon as I find some time.
I haven’t decided yet. It is not open source tho.
after uploading a few files, it has now an error
Was it a pdf with images? This could cause that to happen
yes
It currently only works with text pdfs
hope can support more languages
finally got around to fixing the encoding error and the downloading audio error. It works much smoother now hopefully. Thank you much for your feedback
I will be adding that soon but only as the audio transcription at first
Do you know any solution that work with pdf images, i mean scan of old book.
@gleaming yoke Image OCR to text services like what Google API could do.
what a nice price for 200 pages
thanks for sharing . when you mean google API , You think about ?
OCR and YouTube actually
Yeah unstructured library works well with image pdfs. It uses detectron + tesseract.
hi memo, thanks you for answering. just to be clear, i can use unstructured library for organize image pdf, with detectron and Tesseract applications
yeah you can even use langchain to make it easier to load the docs: You still have to install unstructured tho
i will look that monday thank you very much for providing some information to me