Procedures for running faster-whisper without a GPU: Making transcription practical with CPU and int8 quantization

Even in environments without a GPU, if you combine faster-whisper's CPU inference with int8 quantization and audio ...
GitHub

ten-vad.md

TEN VAD 是 Agora / TEN 生态出的帧级语音活动检测库：每送进 10 ms 或 16 ms 的 16 kHz 音频，返回一个语音概率和 0/1 标志。它只回答 ...
GitHub

Live Transcribe

Real-time transcription of Windows system audio, with one-click toggle, append-only daily transcript files, and hotkey clipboard copy. Runs fully offline on the local ...
blog.csdn

Python中文语音识别实战：Whisper本地部署与调优指南

本内容遵循CC 4.0 BY-SA版权协议 简介：本资源是一套基于Python实现的中文语音识别系统开源项目，面向人工智能初学者、语音处理方向研究生及工程实践者，解决从声学建模到语言建模的端到端 ...