The best Hacker News stories from Show from the past day
Latest posts:
Show HN: Bulk Creation of Transcripts from YouTube Playlists with Whisper
I know there are various tools that are supposed to make this easy, but I couldn't find anything that did everything I wanted, so I made this today for fun. The web-based offerings all take forever and seem flaky, and you need to process one video at a time, with no control over the transcription settings. In contrast, my script lets you convert a whole playlist in bulk with full control over everything.<p>It's truly easy to use-- you can clone the repo, install to a venv, and be generating a folder full of high quality transcript text files in under 5 minutes. All you need to do is supply the URL to a YouTube playlist or to an individual video file and this tool does the rest automatically. It uses faster-whisper with a high beam_size, so it's a bit slower than you might expect, but this does result in higher accuracy. The best way to use this is to take an existing playlist, or create a new one on YouTube, start this script up, and come back the next morning with all your finished transcripts. It attempts to "upgrade" the output of whisper by taking all the transcript segments, gluing them together, and then splitting them back into sentences (it uses Spacy for this, or a simpler regex-based function). You end up with a single text file with the full transcript all ready to go for each video in the playlist, with a sensible file name based on the title of the video.<p>If you have CUDA installed, it will try to use it, but as with all things CUDA, it's annoyingly fragile and picky, so don't be surprised if you get a CUDA error even if you know for a fact CUDA is installed on your system. If you're looking for reliability, disable CUDA. But if you need to transcribe a LOT of transcripts, it does go much, much faster on a GPU.<p>Even if you don't have a GPU, if you have a powerful machine with a lot of RAM and cores, this script will fully saturate them and can download and process multiple videos at the same time. The default settings are pretty good for that situation. But if you have a slower machine, you might want to use a smaller Whisper model (like `base.en` or even `tiny.en`) and dial down the beam_size to 2.
Show HN: Bulk Creation of Transcripts from YouTube Playlists with Whisper
I know there are various tools that are supposed to make this easy, but I couldn't find anything that did everything I wanted, so I made this today for fun. The web-based offerings all take forever and seem flaky, and you need to process one video at a time, with no control over the transcription settings. In contrast, my script lets you convert a whole playlist in bulk with full control over everything.<p>It's truly easy to use-- you can clone the repo, install to a venv, and be generating a folder full of high quality transcript text files in under 5 minutes. All you need to do is supply the URL to a YouTube playlist or to an individual video file and this tool does the rest automatically. It uses faster-whisper with a high beam_size, so it's a bit slower than you might expect, but this does result in higher accuracy. The best way to use this is to take an existing playlist, or create a new one on YouTube, start this script up, and come back the next morning with all your finished transcripts. It attempts to "upgrade" the output of whisper by taking all the transcript segments, gluing them together, and then splitting them back into sentences (it uses Spacy for this, or a simpler regex-based function). You end up with a single text file with the full transcript all ready to go for each video in the playlist, with a sensible file name based on the title of the video.<p>If you have CUDA installed, it will try to use it, but as with all things CUDA, it's annoyingly fragile and picky, so don't be surprised if you get a CUDA error even if you know for a fact CUDA is installed on your system. If you're looking for reliability, disable CUDA. But if you need to transcribe a LOT of transcripts, it does go much, much faster on a GPU.<p>Even if you don't have a GPU, if you have a powerful machine with a lot of RAM and cores, this script will fully saturate them and can download and process multiple videos at the same time. The default settings are pretty good for that situation. But if you have a slower machine, you might want to use a smaller Whisper model (like `base.en` or even `tiny.en`) and dial down the beam_size to 2.
Show HN: LLM Verified with Monte Carlo Tree Search
This is a weekend hack that I'd like to further develop as it's working surprisingly well.<p>Using MCTS, we can explore a space of possible verified programs with an LLM. We check the partial programs at each step, and so steer towards programs that pass the verifier.<p><a href="https://github.com/namin/llm-verified-with-monte-carlo-tree-search">https://github.com/namin/llm-verified-with-monte-carlo-tree-...</a>
Show HN: LLM Verified with Monte Carlo Tree Search
This is a weekend hack that I'd like to further develop as it's working surprisingly well.<p>Using MCTS, we can explore a space of possible verified programs with an LLM. We check the partial programs at each step, and so steer towards programs that pass the verifier.<p><a href="https://github.com/namin/llm-verified-with-monte-carlo-tree-search">https://github.com/namin/llm-verified-with-monte-carlo-tree-...</a>
Show HN: Open-source digital stylus with six degrees of freedom
Show HN: Open-source digital stylus with six degrees of freedom
Show HN: Open-source digital stylus with six degrees of freedom
Show HN: Open-source digital stylus with six degrees of freedom
Show HN: Koelsynth – a simple FM synthesis library
This is part of my journey on pybind11. I wrote a tiny FM Synthesis library in C++ and a Python wrapper for that using pybind11.<p>There is a command-line piano app in the examples directory if you want to play with it. Here is the link: <a href="https://github.com/charstorm/koelsynth/tree/main/examples/simple">https://github.com/charstorm/koelsynth/tree/main/examples/si...</a><p>My next target is to attach this to some kind of physics simulation - like a bunch of balls moving around in a box with some internal walls. When the ball hits certain trigger points, it produces the sound.
Show HN: Koelsynth – a simple FM synthesis library
This is part of my journey on pybind11. I wrote a tiny FM Synthesis library in C++ and a Python wrapper for that using pybind11.<p>There is a command-line piano app in the examples directory if you want to play with it. Here is the link: <a href="https://github.com/charstorm/koelsynth/tree/main/examples/simple">https://github.com/charstorm/koelsynth/tree/main/examples/si...</a><p>My next target is to attach this to some kind of physics simulation - like a bunch of balls moving around in a box with some internal walls. When the ball hits certain trigger points, it produces the sound.
Show HN: I built a Hacker News inspired newsboard for AI and robotics
Hey my name is Crisa and this is my first post here on HN. I love this site and it inspired me to build a clone of it for my newsletter. Instead of having a boring landing page, I hope to gather articles, blogs, interesting projects on my own platform. I would appreciate any feedback, good or bad so that I can improve the site.
Email: gazcrisa (at) gmail (dot) com
Show HN: I built a Hacker News inspired newsboard for AI and robotics
Hey my name is Crisa and this is my first post here on HN. I love this site and it inspired me to build a clone of it for my newsletter. Instead of having a boring landing page, I hope to gather articles, blogs, interesting projects on my own platform. I would appreciate any feedback, good or bad so that I can improve the site.
Email: gazcrisa (at) gmail (dot) com
Show HN: Generate pdf with gitbook or mdbook url
Show HN: Generate pdf with gitbook or mdbook url
Show HN: Generate pdf with gitbook or mdbook url
Show HN: Flyscrape – A standalone and scriptable web scraper in Go
Show HN: Flyscrape – A standalone and scriptable web scraper in Go
Show HN: Flyscrape – A standalone and scriptable web scraper in Go
Show HN: Flyscrape – A standalone and scriptable web scraper in Go
Show HN: DataSheetGrid, an Airtable-like React component
I've built and have been maintaining a React component that renders an Airtable / Notion-like component for a few years.<p>This can be seen as an <input/> where the value is an array of objects.
You can then specify any number of columns that are each responsible for rendering an input for a specific key.<p>The component handles all accessibility features like keyboard navigation, adding / removing rows, context menu, virtualization...<p>If you ever need your users to input long lists of data, this might be a good way to render the form!