Show HN: Caramel: a speech-to-speech conversation model trained only on audio
I trained a speech-to-speech model last night, inspired by Dessa. I'm calling the model caramel-1. The model learned from recordings of people talking and nothing else, and has never seen a single word of text. The code, the training recipe and the weights are open source.<p>caramel-1 sounds incredibly human. Most of what caramel-1 says doesn't make sense yet, but the sentences make a little more sense every time I add more data.<p>Caramel is fast. On a GPU, caramel-1 makes 1 second of audio in about 0.09 seconds, which is fast enough to talk to a real person live. It even works on my MacBook Pro (M3 Pro): running two copies at once, it makes 1 second of conversation in about 0.25 seconds.
Competitors & alternatives
Show HN: PaperMono, e-ink fridge magnet shopping list with mobile web page
Fridge magnet shopping list on an M5Stack PaperMono (ESP32-S3, e-ink touchscreen), synced with a phone web app over Wi-…
Show HN: Pauseless – Free silence/filler-word remover from videos, on-browser
I have been using some third part tools for the purpose of cutting out the silences and filler words from my amateur po…
Show HN: Breadcrumb, record everything on your mac + context manager for AI
Hi HN, I'm Justin.<p>Breadcrumb records everything you do on your Mac (screen + meetings + AI transcripts + what you an…
Show HN: An open virtual office to cowork with humans while your agents work
Hi everyone,<p>I've spent the past several months working alone with AI, and it started getting to me a little. The mac…
Show HN: A decent text-to-image model trained for ~$20K (Apache 2.0 Weights)
My brother and I run a 2-person lab that trains our own generative video models from scratch. The ultimate goal is a se…