The problem with many STT models is that they seem to mostly be trained on perfectly-accented speech and struggle a lot with foreign accents so I’m curious to try this one as a Frenchman with a rather French English accent.
So far, the best I have found while testing models for my language learning app (Copycat Cafe) is Soniox. All others performed badly for non native accents. The worst were whisper-based models because they hallucinate when they misunderstand and tend to come up with random phrases that have nothing to do with the topic.
As a indie hacker/SaaS founder, I have found it surprisingly useful. Allowed me to connect with likeminded people, gain customers, discuss interesting topics. With the right circle, LinkedIn can actually be nice.
I don’t necessarily agree with his political opinions. And that’s a huge understatement.
But DHH has, and continues, to do a lot to share his obvious passion and endless curiosity for tech. I’m not going to stop following him and enjoying his work just because he is not as woke as I am. Politics is not everything.
Ironically, that’s exactly how I feel going to a pub. I don’t really care for beer so anything works for me but I’m often expected to choose from many.
Maybe I’m just not your target customer but I honestly have no idea why I would want to replace DocuSign or how your tool is different. You may want to clarify your positioning.
Getting customers is the main goal but I’m lucky enough to have an existing SaaS that pays the bills on autopilot so I can afford to learn and not get results nearly as fast.
Right now, an AI tool that generates mockups for branding agencies. But I’m still validating the idea so who knows. Ideally, I would like a stack that would work for most SaaS I may think of building. Tempted to give Elixir Phoenix a try. I briefly tried it a few years back and it just felt right.
That’s a good point about the integration. I mostly need to make API calls and have an app that’s easy enough to maintain as a solo founder so it’s mostly a matter of finding the stack that feels right.
Thanks! The thing is, I like ROR but I don’t love it. As in, I like it a lot better than full stack JS but it doesn’t feel quite right. That’s why I’m tempted to give Elixir Phoenix a try.
So far, the best I have found while testing models for my language learning app (Copycat Cafe) is Soniox. All others performed badly for non native accents. The worst were whisper-based models because they hallucinate when they misunderstand and tend to come up with random phrases that have nothing to do with the topic.