Replace Encodec decoding with Vocos #34
Merged
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
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Outdated suggestions cannot be applied.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.
This PR replaces the Encodec decoding with Vocos (https://github.com/charactr-platform/vocos).
In "utils/generation.py" file,
generate_audioandgenerate_audio_from_long_textnow both use Vocos decoding.The dependency on Encodec isn't able to be fully replaced because Vocos doesn't have a way to encode.
My limited testing with a 4090 indicates that Vocos decoding is just marginally slower than Encodec decoding, but the increase in quality more than makes up for it I think.
I am attaching some generated audio samples so you can hear the difference the new decoder makes. This PR does not implement upsampling from 24k to 44.1k as recommended by the Vocos examples, but I have included a few generations that were upsampled to 44.1k in the samples zip.
samples.zip