Step ASR

An ASR model with strong Chinese and English recognition. It distinguishes speech from noise and supports mixed Chinese-English speech and heavily accented Mandarin for voice input, voice control, an…

stepFun/step-asr

An ASR model with strong Chinese and English recognition. It distinguishes speech from noise and supports mixed Chinese-English speech and heavily accented Mandarin for voice input, voice control, and meeting transcription.

Specifications & capabilities

Input
audio
Output
transcription
Published model ID
step-asr
Capabilities
audioInput, transcription

Provider specifications & access

1–1 / 1

Step ASR ↗

source model id
step-asr
hosting
stepfun-global-hosted
platforms
  • StepFun
architecture
input_modalities
  • audio
output_modalities
  • transcription
capabilities
  • audioInput
  • transcription

Original sources

1–2 / 2

StepFun · Model documentation ↗

StepFun · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

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.

Install TensorTrace