{"adoption": {"forks": 135, "observed_at": "2026-08-28T04:04:45.691972+00:00", "stars": 1449}, "canonical_url": "https://ross.abutalabs.com/products/speecht5", "card": {"archived": false, "artifact_type": "library", "description": "Unified-Modal Speech-Text Pre-Training for Spoken Language Processing", "domain": ["speech-processing", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["speech-recognition", "tts", "machine-learning", "deep-learning", "transformers"], "health_score": 20, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["microsoft/SpeechT5"], "name": "microsoft/SpeechT5", "platform": ["python"], "pushed_at": "2024-04-24T05:27:36+00:00", "repo": "microsoft/SpeechT5", "stars": 1449, "tags": ["speech-text-pretraining", "speech-synthesis", "speech-translation", "asr", "research-code", "huggingface", "natural-language-processing", "linux", "gpu"], "topics": ["speech-pretraining", "speech2c", "speecht5", "speechlm", "speechut", "speech-recognition", "speech-synthesis", "speech-translation", "speech-text-pretraining", "vallex", "vatlm"], "urls": [], "use_cases": ["convert text to speech with a pretrained tts model", "transcribe speech to text with asr", "translate speech directly to another language", "clone a voice across languages", "pretrain speech and text models jointly", "run speecht5 models from huggingface"], "what_it_is": "Microsoft's unified-modal speech-text pre-training framework implementing SpeechT5 and related models (SpeechLM, SpeechUT, VALL-E X, WavLLM) for speech recognition, synthesis, and translation. It provides research code, pretrained models, and HuggingFace integration for spoken language processing tasks.", "when_to_avoid": ["you need a production-ready, well-supported TTS/ASR product", "you want simple inference without GPU resources or research setup", "you need actively maintained code with frequent updates"], "when_to_choose": ["you need research-grade pretrained models for ASR, TTS, or speech translation", "you want to reproduce or build on Microsoft's speech-text pre-training papers", "you want HuggingFace-compatible SpeechT5 checkpoints"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/speecht5", "repo": "microsoft/SpeechT5", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:45.691972+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:36:00.420604+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "87a89a94643749e9c7f8ffe9cb4427850e40c401d98c9d463e4b39dc3ef791b4", "fetched_at": "2026-08-28T04:04:45.691972+00:00", "kind": "readme", "missing": false, "url": "https://github.com/microsoft/SpeechT5"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "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": 1667, "days_push": 861, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}