{"data":{"slug":"jishengpeng-wavtokenizer","name":"WavTokenizer","tagline":"[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling","github_url":"https://github.com/jishengpeng/WavTokenizer","owner":"jishengpeng","repo":"WavTokenizer","owner_avatar_url":"https://avatars.githubusercontent.com/u/78149477?v=4","primary_language":"Python","stars":1307,"forks":113,"topics":["acoustic","audio-representation","codec","dac","encodec","gpt4o","music-representation-learning","semantic","soundstream","speech-language-model","speech-representation","text-to-speech"],"archived":false,"github_pushed_at":"2025-03-02T03:53:58+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/jishengpeng-wavtokenizer","markdown_url":"https://www.graphcanon.com/tools/jishengpeng-wavtokenizer.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/jishengpeng-wavtokenizer","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=jishengpeng-wavtokenizer","description":"[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling ","homepage_url":null,"license":"MIT","open_issues":72,"watchers":23,"ai_summary":null,"readme_excerpt":"## Installation\n\nTo use WavTokenizer, install it using:\n\n```bash\nconda create -n wavtokenizer python=3.9\nconda activate wavtokenizer\npip install -r requirements.txt\n```","github_created_at":"2024-08-29T13:45:44+00:00","created_at":"2026-07-11T12:12:34.001521+00:00","updated_at":"2026-07-11T12:12:40.510004+00:00","categories":[{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"semantic","name":"semantic"},{"slug":"codec","name":"codec"},{"slug":"gpt4o","name":"gpt4o"},{"slug":"audio-representation","name":"audio-representation"},{"slug":"acoustic","name":"acoustic"},{"slug":"dac","name":"dac"},{"slug":"music-representation-learning","name":"music-representation-learning"},{"slug":"encodec","name":"encodec"}],"trust":{"provenance":{"is_fork":false,"github_id":849379735,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T12:12:34.632Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":496,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":78,"high_count":0,"last_scan_at":"2026-07-11T12:12:38.094Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T12:12:37.713Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-11T12:12:37.713Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T12:12:37.713Z"}}}}