Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Input sample rate 8kHz #104

Open
ray2510 opened this issue Nov 17, 2023 · 2 comments
Open

Input sample rate 8kHz #104

ray2510 opened this issue Nov 17, 2023 · 2 comments

Comments

@ray2510
Copy link

ray2510 commented Nov 17, 2023

Hi, I noticed there are two modes: Audio for 48kHz and Speech for 16kHz. Would the score be accurate if both the reference and degraded samples were at an 8kHz sample rate in speech mode?

I received this message when I attempted to use an 8kHz sample rate for both the reference and degraded samples.
[equivalent_rectangular_bandwidth.cc : 33] RAW: EquivalentRectangularBandwidth::MakeFilters high_freq >= (sample_rate / 2), for sample_rate=8000 high_freq=8000.000000. Falling back to (sample_rate / 2)

I'm unsure about the meaning of 'Use a wideband model (sensitive up to 8kHz) with voice activity detection.'
Thanks!

@DingWeiPeng
Copy link

Hello, could you please share the binary package of visqol? Building it on linux and window both happens errors. I am a little of crazy

@GitYesm
Copy link

GitYesm commented Jan 25, 2024

Hi, I noticed there are two modes: Audio for 48kHz and Speech for 16kHz. Would the score be accurate if both the reference and degraded samples were at an 8kHz sample rate in speech mode?

I received this message when I attempted to use an 8kHz sample rate for both the reference and degraded samples. [equivalent_rectangular_bandwidth.cc : 33] RAW: EquivalentRectangularBandwidth::MakeFilters high_freq >= (sample_rate / 2), for sample_rate=8000 high_freq=8000.000000. Falling back to (sample_rate / 2)

I'm unsure about the meaning of 'Use a wideband model (sensitive up to 8kHz) with voice activity detection.' Thanks!

I don't think the model is accurate in testing narrow bands

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants