Inference · speech to text

Kannada (ಕನ್ನಡ) speech to text.

Every open model that has done speech to text in Kannada on the network, fastest first. Speed is how many times faster than real time the machine produced it; below 1× it is slower than real time.

3models
ModelFamilySpeedMachines
Whisper large-v3Whisper5.1× real time1
Seamless M4T v2 Large (speech → text)Seamless M4T v20.2× real time3
Whisper large-v3-turboWhisper0.1× real time6