alphacep / alphacep/vosk-api

hardware dependend recognition problems: M$ Surface versus Logitech Webcam C925e

Abierto
#809 5 comentarios 0 reacciones 0 asignados Ver en GitHub
Lenguaje dominante
Jupyter Notebook
Estrellas
15.1k
Forks
1.8k
Métricas de merge de PR
Sin PR fusionados en 30 d

Descripción

Different recording hardware seems to make a big difference in the overall accuracy.

On an AMD Ryzen5 with a Logitech C925e as input device at ~75% loudness level, the accuracy of the word "carola" with the current big german model is excellent, not perfect, but with 95% fine to use. This system has an nvidia card installed.

The same model on an i7 i915 chipset Surface Tablet with ~ the same word "carola" has a really bad recognition rate of ~30%. On the surface we don't have an nvidia device installed.

A tool to determine the perfect audio level of the microphone for recognition and a test tool for the hardware support would be nice. This could make debugging recognition mistakes a lot easier.

Guía de contribución

No hay ninguna guía de contribución indexada para este repositorio

Evaluación

Este issue todavía no se ha evaluado.

Recibe los nuevos issues en tu correo

Un resumen breve de issues de GitHub para principiantes.