{"adoption": {"forks": 74, "observed_at": "2026-09-03T02:15:20.754553+00:00", "stars": 1136}, "canonical_url": "https://ross.abutalabs.com/products/mega-asr", "card": {"archived": false, "artifact_type": "library", "description": "First foundation ASR built for the real world - 7 atomic acoustic conditions, 54 compound scenarios, 2.6M samples, and up to ~30% gains over SOTA where every other model falls apart. **You'll come back to MEGA-ASR, after the rest fail in the wild. ⭐**", "domain": ["speech-processing", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["speech-recognition", "machine-learning", "deep-learning", "llm-training", "data-generation"], "health_score": 80, "homepage": "https://xzf-thu.github.io/Mega-ASR/", "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["xzf-thu/Mega-ASR"], "name": "xzf-thu/Mega-ASR", "platform": ["python"], "pushed_at": "2026-09-02T06:19:55+00:00", "repo": "xzf-thu/Mega-ASR", "stars": 1136, "tags": ["asr", "robust-speech-recognition", "acoustic-simulation", "foundation-model", "reinforcement-learning", "dataset", "model-weights", "audio", "gpu", "linux"], "topics": ["asr", "robust"], "urls": [], "use_cases": ["transcribe speech in noisy real-world environments", "recognize far-field or reverberant audio", "evaluate ASR robustness across acoustic conditions", "train a robust speech recognition model", "benchmark ASR models against challenging audio", "download open ASR model weights"], "what_it_is": "Mega-ASR is a foundation automatic speech recognition model trained on 2.6M samples spanning 7 atomic acoustic conditions and 54 compound real-world scenarios, using A2S-SFT and DG-WGPO reinforcement learning. The repository provides training code, model weights, and an associated dataset and benchmark for robust in-the-wild speech recognition.", "when_to_avoid": ["you need a lightweight ASR for clean studio audio", "you require a permissive license - the repo has no license", "you need streaming or low-latency on-device transcription"], "when_to_choose": ["your ASR pipeline fails on noisy, far-field, or distorted real-world audio", "you need a robust open ASR foundation model with weights and training data", "you want to benchmark speech recognition under compound acoustic scenarios"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mega-asr", "repo": "xzf-thu/Mega-ASR", "role": "main", "score": 59}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-09-03T02:15:20.754553+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:37:54.945657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "1b4960e365cf14ff9c372e5a0f945283f072b66ca55fce0d7f4f54918b2dfa3e", "fetched_at": "2026-09-03T02:15:20.754553+00:00", "kind": "readme", "missing": false, "url": "https://github.com/xzf-thu/Mega-ASR"}, {"content_hash": "0846541fa75af7c400a91e432db95d0c32fe6c0bd1239a1b00638cc9f3ad0a84", "fetched_at": "2026-08-29T12:42:23.727632+00:00", "kind": "homepage", "missing": false, "url": "https://xzf-thu.github.io/Mega-ASR/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 100, "longevity": 7, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "young", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 109, "days_push": 0, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 59, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 3, "stale_scrape": false}}