- This topic has 2 replies, 2 voices, and was last updated 7 years, 7 months ago by .
Viewing 3 posts - 1 through 3 (of 3 total)
Advertisement: “RapidEars is an OpenEars™ plugin that lets you perform speech recognition while the user is still speaking!”
-
Posts
-
I have a 6000+ words list to recognize. I use the AcousticModelChinese to complete my task. While the 80 percent of recognitions are correct, that’s not enough for me. I find a list of arguments in cmd tool of pocket sphinx. Are there any arguments I can adjust to make my recognitions more precise?
By the way, I have tried to set vadThreshold to 3.5 as you guys early mentioned. It really helps me!Welcome,
Thank you for sharing your results, they are pretty good already for such a large task and it’s good to hear. I would recommend searching these forums for the keyword “accuracy” and looking through the FAQ: https://www.politepix.com/openears/support to see if there are some improvements I’ve already described.
Viewing 3 posts - 1 through 3 (of 3 total)
- You must be logged in to reply to this topic.