nodejs-whisper
nodejs-whisper copied to clipboard
NodeJS Bindings for Whisper - the CPU version of OpenAI's Whisper, as initially crafted in C++ by ggerganov.
Hello, this might or might not be a bug, but I wanted to mention it as this package could be well used in combination with `node-mic` as well. ```ts import...
Hi thanks for this great library. I would like to pass the language for the transcription. Is this option available? I notice the large model tries to automatically detect the...
 main.exe -m C:\Developer\Pruebas\whipser-test\node_modules\nodejs-whisper\cpp\whisper.cpp\models\ggml-tiny.bin -f C:\Developer\Pruebas\whipser-test\node_modules\nodejs-whisper\cpp\whisper.cpp\samples\jfk.wav [Nodejs-whisper] Attempting to compile model... "cc" no se reconoce como un comando interno o externo, programa o archivo por lotes ejecutable. "head" no se...
I try to speech to text using nodejs-whisper and I got success with the below code and I checked the log get the message `[Nodejs-whisper] Transcribing Done!` Now what to...
I am on a Mac and trying to use this in a nextjs project Code ` const filePath = path.join(tempDir, 'out.wav'); console.log(filePath) // generate the transcript with whisper const transcript...
``` > [email protected] start > npx tsx src/index.ts [Nodejs-whisper] Transcribing file: F:\Projects\Whisper\karasmsk.25.mp4 [Nodejs-whisper] Converting audio to wav File Type... [Nodejs-whisper] whisper.cpp not initialized. F:\Projects\Whisper\node_modules\nodejs-whisper\dist [Nodejs-whisper] Attempting to run 'make' command...
Bumps [@types/node](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/node) from 22.1.0 to 22.2.0. Commits See full diff in compare view [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter...
@ChetanXpro is there any way to improve this time consuming process for hindi language audio transcription ? and sometime line are repeated or words not displaying and music time/blank/silent audio...
Is it possible to get word from hindi audio as well! if yes then how ?
Is it possible to get a feature where we can init / load the model once and use the loaded model? Right now, every call reloads the model right?