- Видео 29
- Просмотров 52 745
Christian Groll
Добавлен 14 янв 2013
Видео
Retrieval Augmented Generation Part 1
Просмотров 254 месяца назад
Retrieval Augmented Generation Part 1
Retrieval Augmented Generation Part 2
Просмотров 154 месяца назад
Retrieval Augmented Generation Part 2
Fehlendes Wissen als Herausforderung von LLMs
Просмотров 175 месяцев назад
Fehlendes Wissen als Herausforderung von LLMs
Software as a service, Teil 2 - Beispiel einer Software Architektur
Просмотров 23Год назад
Serverless backend with authentication, GDPR
Software as a service, Teil 1 - Frontend, Backend, Database und Authentifizierung
Просмотров 91Год назад
Introduction to software architecture with frontend, backend, database and authentication
02 Record wav file
Просмотров 257Год назад
This video is part of a series that shows how to automatically transcribe mp3/wav podcasts with Python using whisper and pyannote In this part we will use Python to record some audio and store it as wav file. Thereby I use: - Visual Studio Code - Jupyter extension for convenient cell mode - magit for git commands Some of the code was simply copied from stackoverflow.com/questions/40704026/voice...
01 Initialize project and computing environment
Просмотров 386Год назад
Building a data science product with python: Transcription of audio conversations This video is part of a series that shows how to automatically transcribe mp3/wav podcasts with Python using whisper and pyannote In this part we get started with our project. For this we: - create a project from the data science cookiecutter template: drivendata.github.io/cookiecutter-data-science/ - initialize g...
03 Apply whisper and download mp3 podcast
Просмотров 277Год назад
Building a data science product with python: Transcription of audio conversations This video is part of a series that shows how to automatically transcribe mp3/wav podcasts with Python using whisper and pyannote In this part we: - install and apply whisper to .wav file - introduce the podcast search engine www.listennotes.com/ - learn how to get podcast file urls from podcast rss feeds on liste...
06 Introduction to Pyannote
Просмотров 2,9 тыс.Год назад
Building a data science product with python: Transcription of audio conversations This video is part of a series that shows how to automatically transcribe mp3/wav podcasts with Python using whisper and pyannote In this part we'll talk about pyannote, a python package for speaker diarization. We'll first look at several segmentation usecases and then talk about how one might use this segmentati...
05 Use whisper with text segments
Просмотров 589Год назад
Building a data science product with python: Transcription of audio conversations This video is part of a series that shows how to automatically transcribe mp3/wav podcasts with Python using whisper and pyannote In this part we'll apply whisper to a podcast file in order to get a transcript with segments and timestamps. We'll also use pandas to keep track of all outputs in DataFrame format. #wh...
04 Transfrom mp3 to wav and crop audio
Просмотров 203Год назад
Building a data science product with python: Transcription of audio conversations This video is part of a series that shows how to automatically transcribe mp3/wav podcasts with Python using whisper and pyannote In this part we'll: - download and write mp3 to disk for a given file name - show debugging with visual studio code - transform a mp3 file to a wav file - crop a wav file Code is based ...
11 Generate more human-readable outputs
Просмотров 212Год назад
11 Generate more human-readable outputs
10 Get maximum overlaps for text and speaker segments
Просмотров 273Год назад
10 Get maximum overlaps for text and speaker segments
08 Create standardized Dataframe output for pyannote model
Просмотров 477Год назад
08 Create standardized Dataframe output for pyannote model
Kickoff: Building a data science product with python - Transcription of audio conversations
Просмотров 645Год назад
Kickoff: Building a data science product with python - Transcription of audio conversations
markdown to html slides using pandoc
Просмотров 3,3 тыс.9 лет назад
markdown to html slides using pandoc
thanks for this video.
Great Video Christian
and the explanation is also too gooooooood
thanks a lot sir you made my task too much easier
Vielen Dank !!
where can I get what was said by who?? i only see graphs and a table with time/speaker but not what was said
Have you considered segmenting the audio into separate chunks pased on the results of the speaker diarization and sending those chunks to the the whisper model for transcription? That would spare you the work of having to combine the two dataframes (of course it introduces other work that would need to be done)?
Any idea how to dockerize pyannote models?
Thank you for those! Apreciate your guide. Love this series. Cheers!
I was difficult to understand, however, useful
I ran this, and it wasn't as accurate at labeling speakers. sometimes it couldn't distinguish who said what and would label "Speaker 1" even though the other person had said it. I think you can train it further for better results.
hi, how to use pandas to check the json output in whisper? can you give a more detail way? as a python developer, i only use vs code, and python debug is shit. Each time i have to run my command manually and print to see if everything is fine.
I like the approach - yes, it might be slow, but you are very systematic (my father might say “very German” 😊) with it and I have a feeling it will help me. I hope I will be able to use combination of Pyannote and Whisper APi, without running Whisper from my machine?
Great video!
Hello thank you for this video, my latex file is compiled only with xelatex how to convert it to epub
Thanks for the video !
Can't believe for a developer create a desktop shortcut could be so hard, uninstalled btw
thank you very much. In case MiKTeX is not already installed, the command ‘pandoc -t beamer -f markdown slides.md -o example.pdf’ will throw the error ’error: pdflatex not found’. The instructions from this link fixes the problem: stackoverflow.com/questions/29240290/pandoc-for-windows-pdflatex-not-found
can you help me with this? When I am trying to execute the command pkg.add("IJulia"), it says "pkg not defined".
try "using Pkg; Pkg.add("IJulia")
thk u..... great job....
Thank you so much you are the one and only one who has done this job perfectly
the link is - github.com/JuliaLang/IJulia.jl
thank you Very good! helped a lot
Great video!, a little question, Could you suggest a good video or manual to learn to program in the command line, please?
Thank you
Thank you.
thank you for the help...
I have Julia correctly installed on my win8.1, I did all you described in the video and the light table connect to Julia when you switch on it. But unfortunately when I type anything on a new script it doesn't give me any result. Despite the fact that Light table says that is connected with Julia, it seems to work as notepad editor. Do you have any idea of what's wrong?
Hi, ctrl+enter to see the result!
I cannot find the juno from the show pluginmanager.What should I do? Thanks in advance
Hi, press enter to search it!
I hope you do not remove this video, bcz already added into my favorite.