Whistle: Speech to Text in 16.9 MB https://cactuscompute.com/blog/whistle It's not great yet, but for the size it's pretty impressive.
cactuscompute.comWhistle: Speech to Text in 16.9 MBAn open speech recognition model that runs on the same CPU engine as Needle. It transcribes seven languages, reaches the first token in 11 ms, and loads beside Needle so one binary turns a clip straight into tool calls.
0 reposts2 likes