Inference · speech to text

English speech to text.

Every open model that has done speech to text in English 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.

8models
ModelFamilySpeedMachines
moonshine tinyMoonshine41× real time6
Whisper large-v3Whisper5.1× real time1
moonshine baseMoonshine4.7× real time5
Whisper smallWhisper0.4× real time3
Seamless M4T v2 Large (speech → text)Seamless M4T v20.2× real time3
Whisper large-v3-turboWhisper0.1× real time6
Whisper mediumWhisper0.1× real time2
MiniCPM-o 4.5 BASEMiniCPM-o 4.5measured2