webassembly009 transformers.js 网页端侧推理 whisper-web

whisper-web

• https://github.com/xenova/whisper-web

页面结构

• AudioManager: 该组件负责音频的录制和处理。它会使用 Web API 来访问麦克风，录制音频数据，并将其传递给 transcriber 进行转录。它通过 transcriber 管理转录状态，音频数据将在转录过程中传输和处理。

• Transcript: 该组件负责展示转录结果。transcribedData 是来自 transcriber.output 的转录文本，它会在屏幕上动态更新。

CG

• webassembly009 transformers.js 网页端侧推理
• https://hugging-face.cn/docs/transformers.js/index
• https://whisper-web.netlify.app/
• https://github.com/hexgrad/kokoro：Kokoro is an open-weight TTS model with 82 million parameters. Despite its lightweight architecture, it delivers comparable quality to larger models while being significantly faster and more cost-efficient. With Apache-licensed weights, Kokoro can be deployed anywhere from production environments to personal projects.