Transcript: So I'm going to record on my voice notes here, and then I'm going to send this off to be transcribed, and it's going to happen ridiculously fast.
88.82% similar
The user finds it incredible how fast voice notes can be transcribed using a specific tool. They are amazed by the speed at which the transcription occurs.
I record a voice memo, which will then be automatically added to my website. Upon summarization, the content of the memo will be uploaded to the site. To initiate this process, I simply need to click. Thus, a voice memo can be easily transformed and shared on my website with just a few actions.
The day started with frustration over poor transcriptions, which were caused by a high-frequency pitch, but fixing the issue improved the transcriptions. The person also shifted the work to their local machine and had a simple lunch of two chicken bakes. They planned to go surfing, but the surf conditions were bad, so they went shopping instead. They bought a board game, The Crew, as a treat and then planned to cook dinner, clean the house, and work on adding edit functionality for a project. They anticipated the task to be relatively simple once they decide on the structure for keys and values.
The speaker is intrigued by the idea of a micro social network and wants to create an app that makes it easier to send voice notes to a small group of friends. They express a keen interest in receiving summaries of voice notes rather than full transcripts and want to cultivate a space for sharing ideas with a select group. They also discuss the possibility of sharing the same voice note with multiple groups and mention their intention to prototype the app. Despite feeling overwhelmed with other tasks, they contemplate swiftly putting together a plan for the micro social network.
I had an excellent call with Jordan, which I'll discuss in more detail later. Unexpectedly, I succeeded in quantizing lava, and the initial results look promising despite the script being rough. It seems feasible that I might run something akin to GPT-4 style vision captioning locally. I'm excited to upload these quantized models to see the outcomes and I plan to head to Jordan's house to upload more models soon.