WavTokenizer
[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
Use WavTokenizer to convert audio into a format suitable for language processing tasks.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytime[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
WavTokenizer has 1.3k stars on GitHub. It has been forked 113 times. WavTokenizer is written mainly in Python. It has been in active development since 2024. WavTokenizer is available under the MIT license. Its main topics are acoustic, audio-representation, codec, dac.
What is WavTokenizer?
[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling
Is WavTokenizer open source?
WavTokenizer is an open-source project. It is released under the MIT license.
Is WavTokenizer free?
Yes. WavTokenizer is free and open source — you can use, modify and self-host it.
What license does WavTokenizer use?
WavTokenizer is available under the MIT license.
What language is WavTokenizer written in?
WavTokenizer is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/jishengpeng-wavtokenizer.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.