Unverified85% confidenceFactTime unknown
Whisper的语音识别模型只能处理16kHz采样率的单声道PCM浮点数据格式的原始音频波形
1
Sources
85%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Unverified在 M1 芯片上运行 Whisper base 模型的转录速度可达音频时长的 10-15 倍，即 1 分钟音频仅需 4-6 秒完成转录73% similarUnverifiedThe sampling rate of audio signals is typically 16 kHz or 44.1 kHz, containing tens of thousands of sample points per second, while the output text sequence contains only approximately 3–5 words per second.72% similarUnverifiedWhisper small模型在现代笔记本电脑的CPU上处理一段10分钟音频通常只需1-3分钟71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/23282API
curl https://kongchang.com/api/v1/knowledge/claims/23282MCP
get_claim(id=23282)