fix sample_rate to frame_rate where appropriate #40
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
facebook-github-bot
added
the
CLA Signed
|
thanks for the fix, that seems like a better name indeed. |
Dinglet
pushed a commit
to Dinglet/encodec
that referenced
this pull request
Jan 25, 2024
* fix sample_rate to frame_rate where appropriate * lint
thatsvenyouknow
pushed a commit
to thatsvenyouknow/neuro-encodec
that referenced
this pull request
Jun 20, 2024
* fix sample_rate to frame_rate where appropriate * lint
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
In the quantizer, each quantizer quantizes a frame with
lg(bins)bits. That means a single quantizer's bandwidth islg(bins) * frame_rate. This aligns with the calculations in #39:For the 24kHz model, frame rate is 75 Hz. Then we expect each quantizer (1024 bins) to contribute 75 * 10 bps, and with a bandwidth of 6kbps we get 6kbps total bandwidth / 750 bps per quantizer = 8 quantizers.
I didn't see anywhere in the codebase that calls the rvq's
forwardfunction but I updated it as well anyways.TODO before review: run tests and lintall the tests and lint passed