{"adoption": {"forks": 387, "observed_at": "2026-08-28T04:07:05.385010+00:00", "stars": 2627}, "canonical_url": "https://ross.abutalabs.com/products/ultralight-digital-human", "card": {"archived": false, "artifact_type": "library", "description": "一个超轻量级、可以在移动端实时运行的数字人模型", "domain": ["deep-learning", "computer-vision", "speech-processing", "mobile-development", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "deep-learning", "speech-recognition", "video-processing", "llm-inference"], "health_score": 76, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["anliyuan/Ultralight-Digital-Human"], "name": "anliyuan/Ultralight-Digital-Human", "platform": ["python", "cross-platform"], "pushed_at": "2026-07-22T12:29:48+00:00", "repo": "anliyuan/Ultralight-Digital-Human", "stars": 2627, "tags": ["digital-human", "talking-head", "audio-driven-video", "real-time-inference", "onnx", "mobile-deployment", "wav2lip-alternative", "streaming-inference", "android", "ios", "gpu"], "topics": [], "urls": [], "use_cases": ["create a talking avatar from a short training video", "run a real-time digital human on a phone", "generate lip-synced video from audio", "build a lightweight virtual presenter or chatbot avatar", "stream a digital human with low latency on mobile", "train a custom talking-head model from my own footage"], "what_it_is": "An ultralight talking-head (digital human) model that animates a person's face from audio input and runs in real time on mobile devices. It uses lightweight audio encoders (wenet/HuBERT) with a UNet-based video generation pipeline, with training and streaming inference scripts in Python.", "when_to_avoid": ["you need high-fidelity, full-body or expressive avatars rather than a single talking face", "your source audio is noisy or has echo, which degrades results significantly", "you need a production-ready, well-licensed package (no explicit license file)", "you want a maintained C++ deployment path out of the box (see the successor FeatherTalk instead)"], "when_to_choose": ["you need a very lightweight, real-time talking-head model on mobile or edge devices", "you want an open-source alternative to commercial digital human APIs", "you have clean audio/video training footage and want a custom avatar", "you need streaming inference with low per-frame latency"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ultralight-digital-human", "repo": "anliyuan/Ultralight-Digital-Human", "role": "main", "score": 64}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.385010+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:19:43.953749+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f421ea59c760a4c89048cc8af5e3cfb8d52241ab185a12bdc8d533de0a888bd9", "fetched_at": "2026-08-28T04:07:05.385010+00:00", "kind": "readme", "missing": false, "url": "https://github.com/anliyuan/Ultralight-Digital-Human"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 93, "longevity": 49, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 692, "days_push": 42, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 64, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}