alphacep / alphacep/vosk-api

Problem with vosk-model-en-us-0.22 model

Open
#1,999 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
15.1k
Forks
1.8k
PR merge metrics
No merged PRs in 30d

Description

Whenever I try to use the model, it never correctly understands the first few words I say.
For example, in one case I started with "**show**", but it interpreted it as:

> “the new item the materials table inside the kitchen database item name water bottle quantity ten in stock zero”

In another example, I started with "**need your**", but it produced:

> “the help a lott”

And in yet another case, when I started with "**show**", it said something like:

> “the omi out of stock items in the ...”

It seems like the model overwrites or ignores the very first token(s) of my speech input and replaces them with “**the**” or some unrelated phrase.

Contributor guide

No contributing guide indexed for this repository

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.