Unverified50% confidenceBenchmarkExact time
With the large-v3 model, transcription speed on a modern laptop CPU using whisper.cpp is about 1–2 times real time, about 3–8 times on Apple Silicon with Metal, and about 15–30 times on a consumer-grade Nvidia GPU using faster-whisper.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/15/2026
First Seen
Valid until: 1/13/2027
Sources
Related Entities
Related Claims
UnverifiedOn an Apple Silicon MacBook Air (M4, 10-core CPU, 16 GB), Whisper large-v3-turbo has an average latency of 0.68 seconds, a real-time factor of 0.095, and a WER of 2.89% (29/1002).79% similarUnverifiedWhisper small模型约有244M参数，在消费级CPU上即可流畅运行73% similarUnverifiedSopro V2 Turbo has a first-audio-output latency of approximately 300 milliseconds on a laptop CPU.71% similarUnverifiedOpenAI's Whisper large-v3 model takes approximately 10–15 minutes to transcribe speech from a 1-hour video on an Apple M2 chip, compared to approximately 2 minutes on a cloud-based A100 GPU.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1035251API
curl https://kongchang.com/api/v1/knowledge/claims/1035251MCP
get_claim(id=1035251)