{"adoption": {"forks": 115, "observed_at": "2026-08-28T04:04:20.898970+00:00", "stars": 1316}, "canonical_url": "https://ross.abutalabs.com/products/wavtokenizer", "card": {"archived": false, "artifact_type": "library", "description": "[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling ", "domain": ["speech-processing", "machine-learning", "large-language-models"], "enriched": true, "function": ["audio-processing", "machine-learning", "serialization", "speech-recognition", "llm-training"], "health_score": 26, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["jishengpeng/WavTokenizer"], "name": "jishengpeng/WavTokenizer", "platform": ["python", "cross-platform"], "pushed_at": "2025-03-02T03:53:58+00:00", "repo": "jishengpeng/WavTokenizer", "stars": 1316, "tags": ["neural-codec", "audio-tokenizer", "text-to-speech", "discrete-tokens", "iclr-2025", "pytorch", "audio", "natural-language-processing"], "topics": ["acoustic", "audio-representation", "codec", "gpt4o", "music-representation-learning", "semantic", "speech-representation", "text-to-speech", "speech-language-model", "dac", "encodec", "soundstream"], "urls": [], "use_cases": ["tokenize speech and audio into discrete codes for audio language models", "reconstruct audio from raw wav files with high fidelity", "build text-to-speech systems with a compact acoustic tokenizer", "replace EnCodec, DAC, or SoundStream with fewer tokens per second", "extract semantic audio representations for speech and music", "train speech language models on discrete audio tokens"], "what_it_is": "WavTokenizer is a state-of-the-art discrete neural audio codec that compresses speech, music, and general audio into only 40 or 75 discrete tokens per second. It is designed as an acoustic tokenizer for audio language models (like GPT-4o-style models) and text-to-speech pipelines, with pretrained checkpoints on Hugging Face.", "when_to_avoid": ["you need real-time streaming codec operation", "you need production-grade audio compression for storage rather than ML tokenization", "you work outside the PyTorch/Python ecosystem"], "when_to_choose": ["you need an extremely low frame rate (40/75 tokens per second) discrete audio representation", "you are building audio language models or TTS systems and need semantic-rich tokens", "you want strong audio reconstruction quality at low bitrates", "you want a drop-in alternative to EnCodec or DAC"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/wavtokenizer", "repo": "jishengpeng/WavTokenizer", "role": "main", "score": 27}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:20.898970+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:48:29.552961+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a00befb18894e44a193e1aaedba241bf08e8b14a5db22acff6fec4819cb948f5", "fetched_at": "2026-08-28T04:04:20.898970+00:00", "kind": "readme", "missing": false, "url": "https://github.com/jishengpeng/WavTokenizer"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 9, "longevity": 52, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 734, "days_push": 549, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 27, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}