stepaudio-2.5-asr-stream ↗
- source model id
- stepaudio-2.5-asr-stream
- hosting
- stepfun-global-hosted
- platforms
- StepFun
- architecture
- input_modalities
- audio
- output_modalities
- transcription
- capabilities
- audioInput
- streaming
- transcription
StepAudio 2.5 ASR is a 4B-parameter speech recognition model. It introduces Multi-Token Prediction (MTP) technology to predict multiple tokens per step in parallel, maintaining SOTA transcription acc…
stepFun/stepaudio-2.5-asr-stream
StepAudio 2.5 ASR is a 4B-parameter speech recognition model. It introduces Multi-Token Prediction (MTP) technology to predict multiple tokens per step in parallel, maintaining SOTA transcription accuracy while dramatically reducing serial wait cycles: a 5-minute audio clip can be fully transcribed in 1 second.
1–1 / 1
1–2 / 2
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.