transcript.fish VS logseq

I have been working on this podcast transcription project for a couple months and it's been super rewarding.

I listen to a podcast called No Such Thing As A Fish, where some researchers talk about their favorite facts they learned that week. Then they riff on it and are generally smart and funny. I listened to the series so many times that I decided I wanted to listen to the show on shuffle, not at the episode level, but at the fact level.

Since I have been playing around with whisper.cpp in python this seemed like a perfect way to combine some technologies I've been wanting to play with.

I ran whisper over the entire podcast and transcribed all the episodes. I had to do this multiple times because I kept messing up. It eventually took like 7 straight days of my M1 processing to get through ~490 episodes.

4 million words, and an 800Mb SQLite database later, I got the transcriptions done and have put up a nice site for searching through the data.

https://transcript.fish

Now I just need to figure out the rest. Breaking it up into facts. Getting the audio working. Highlighting and linking to words, phrases, etc.

Some cool info about the process so far:

1. The SQLite database is chunked up and stored as static files, and the frontend queries the static files directly using HTTP range requests, so it only downloads a couple hundreds kbs when querying.

2. I've been proper using ChatGPT 3.5 free version to help me write python and SQL. It's been pretty game changing as I feel basically no pain from not knowing what I'm doing.

The code is here: https://github.com/noman-land/transcript.fish

Please help if you know how to get whisper speaker diarization working!! I would really appreciate the help.

Interesting, thanks for the tip! I've never heard of lockdown mode. Unfortunately I don't own an iPhone. Any chance you could post an issue with steps to repro?

https://github.com/noman-land/transcript.fish/issues

Thank you!

Logseq support via our Logseq Plugin

Sorry, but _what exactly_ «it seems to do» from your point of view?

My «second brain» now is almost 300Mb of text, pictures, sound files, PDF and other stuff. As I already mentioned, it contains tables, mathematical formulae, sheet music, cross-references, code samples, UML diagrams and graphs in Graphviz format. It is versioned, indexed by local search engine, analyzed by AI assistant and shared between many computers and mobile devices. And (last but not least) it works: it allows me to solve my tasks way more faster than with the assistant of external, non-personalized tools (like ChatGPT, StackExchange or Google).

I know no tools for all this tasks except org-mode. Well, maybe Evernote in the 2010-s was something similar — but with less features, with more bugs and with worse interface.

Personal note-taking _is_ a complex task per se (well, at least for someone like typical HN visitor). I've seen many note-taking tools, that were ridiculously featureless, stupid and inconvenient because they were _not_ complex enough.

> Sure if one wants to do emacs-gardening it is fine.

1)You can use org-mode outside Emacs. See for example Logseq (https://logseq.com/), organice (https://organice.200ok.ch/) or EasyOrg.

2)Org-mode works in Emacs out of the box, you don't need any «emacs-gardening» to use org-mode.

3)The term «Emacs-gardening» itself sound a bit like hate-speech for me. The complexity of Emacs customization is overrated, mostly due to opinions of people who never used Emacs or used it in the previous millennium.

Obsidian is great.

For those looking for an open source alternative (or don't want to pay the Obsidian fees for professional usage) check out Logseq: https://logseq.com/

For an opensource alternative to Obsidian checkout Logseq (1). I spent a while thinking obsidian was opensource out of my own ignorance and was disappointed when I learned it was not.

1: https://logseq.com/

I use logseq to keep journal of my daily work.

While Emacs and Org mode can certainly be used for this (and, when they can't, you can always inject little python/js scripts in your emacs config to take care of specific things), I'd also recommend you take a look at Logseq.