alphacep / alphacep/vosk-api

Using Two Microphones for Speaker Transcription

Aperta
#1,650 1 commento 0 reazioni 0 assegnatari Vedi su GitHub
Lingua principale
Jupyter Notebook
Stelle
15.1k
Fork
1.8k
Metriche di merge delle PR
Nessuna PR unita negli ultimi 30g

Descrizione

Hello,

I am currently working on a project that involves real-time transcription of conversations using the Vosk speech recognition system. I would like to inquire about the possibility of utilizing two different microphones for transcribing Speaker 1 and Speaker 2.

Background
In my setup, I have two different microphones connected to my machine:

Audio Card 1
Audio Card 2

The goal is to capture audio from each microphone separately and transcribe it in real-time, distinguishing between the two speakers. However, I am facing challenges in configuring the Vosk API to handle multiple audio input devices simultaneously.

Questions
Is there support in the Vosk API for handling multiple input devices at the same time?
What are the recommended practices for implementing this feature?
Are there any examples or documentation that outline how to set up two separate audio streams for different microphones?
Any guidance or insights on this issue would be greatly appreciated!

Thank you for your time.

Guida per i contributori

Nessuna guida per i contributori indicizzata per questo repository

Valutazione

Questa issue non è ancora stata valutata.

Ricevi le nuove issue nella tua casella

Un breve riepilogo di issue GitHub adatte ai principianti.