WavTokenizer
[ICLR 2025] State-of-the-art discrete acoustic codec models for audio language modeling
GraphCanon updated Sep 20, 2026 · GitHub synced Sep 20, 2026
39views this month
Decision brief
WavTokenizer is an advanced acoustic codec model adept at audio representation, suitable for developers focusing on precision in speech-language modeling or text-to-speech applications requiring high token throughput.
Good fit when
- Need state-of-the-art precision in audio language modeling
- Projects requiring 40/75 tokens per second processing
Avoid when
- Limited to Python environments;不适合非Python环境的项目
- For simple tasks, it may offer unnecessary complexity
Observed Jul 12, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Dormant (567d since push)
- As of Sep 20, 2026
- Provenance
- Not a fork · Personal account
- As of Sep 20, 2026
- Security (OSV)
- 78 low (78 low)
- As of Jul 11, 2026
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install WavTokenizerSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
WavTokenizer is a leading acoustic codec model with 40/75 tokens per second designed for advanced applications in audio representation and speech-language modeling.
Capability facts
- Languages
- python
Source: github.language · Sep 20, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Sep 20, 2026)
conda create -n wavtokenizer python=3.9Source link
Tags
README
Installation To use WavTokenizer, install it using:
For agents
This page has a .md twin and JSON over the API.