[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795CEW16PZ9PP5P93674B96":3,"skill-same:01M795CEW16PZ9PP5P93674B96":71},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M795CEW16PZ9PP5P93674B96","speechbrain",null,"Guides SpeechBrain package use, pretrained inference, recipes, audio pipelines, model components, metrics, and repo maintenance for speech and conversational-AI workflows.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspeechbrain\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: speechbrain\ndescription: \"Guides SpeechBrain package use, pretrained inference, recipes,\n  audio pipelines, model components, metrics, and repo maintenance for speech\n  and conversational-AI workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# SpeechBrain repo skill\n\nUse this skill when a task involves the SpeechBrain Python package, SpeechBrain recipes, pretrained SpeechBrain models, HyperPyYAML experiment files, audio\u002Fdata pipelines, speech preprocessing, speech metrics, or maintaining the SpeechBrain repository.\n\nSpeechBrain is a PyTorch-based speech and conversational-AI toolkit. It exposes both a library (`speechbrain`) and a large recipe collection. Start here to choose the right focused route, then read only the linked sub-skill\u002Freference needed for the task.\n\n## Quick install and import check\n\nFor ordinary package use:\n\n```bash\npip install speechbrain\npython - \u003C\u003C'PY'\nimport speechbrain as sb\nprint(sb.__version__)\nprint(sb.Brain)\nPY\n```\n\nFor local recipe development from a source checkout, install the repository and its dependencies in an isolated environment:\n\n```bash\npip install -r requirements.txt\npip install --editable .\npython -m pip check\n```\n\nRun the bundled environment smoke script when diagnosing setup or optional dependency issues:\n\n```bash\npython scripts\u002Fcheck_speechbrain_install.py --json\n```\n\nRead `references\u002Finstallation-and-environment.md` for dependency, Python\u002FTorch, audio backend, Hugging Face, and CPU\u002FGPU notes. Read `references\u002Ftroubleshooting.md` for cross-cutting install, import, audio, network\u002Fcache, and runtime failures.\n\n## Route map\n\n| User task | Read |\n| --- | --- |\n| Use pretrained models for ASR, speaker verification, classification, enhancement, separation, VAD, TTS, G2P, or local\u002FHugging Face model loading. | `sub-skills\u002Fpretrained-inference\u002FSKILL.md` |\n| Run or adapt a recipe, create a new recipe from templates, debug HyperPyYAML overrides, use `Brain`, or launch CPU\u002FGPU\u002FDDP training. | `sub-skills\u002Frecipe-training\u002FSKILL.md` |\n| Load\u002Fsave audio, build `DynamicItemDataset`\u002F`DataPipeline`, train tokenizers, create audio features, apply augmentation, beamforming, or vocal-feature preprocessing. | `sub-skills\u002Fdata-audio-pipelines\u002FSKILL.md` |\n| Choose neural blocks, decoders, losses, metric stats, WER scoring, checkpoint recovery, `Pretrainer`, streaming helpers, or component-level tests. | `sub-skills\u002Fcomponents-metrics\u002FSKILL.md` |\n| Maintain the repository: focused tests, recipe CSV consistency, docs generation, performance tables, lint\u002Fpre-commit, or contributor review checks. | `sub-skills\u002Frepo-maintenance\u002FSKILL.md` |\n\n## Working model\n\n- SpeechBrain experiments are usually a Python script plus a HyperPyYAML file: `python train.py hparams.yaml --override value`.\n- `speechbrain.Brain` owns train\u002Fvalid\u002Ftest loops; recipes subclass it and override forward\u002Fobjective hooks.\n- Pretrained inference classes inherit `speechbrain.inference.interfaces.Pretrained` and are commonly loaded with `Class.from_hparams(source=..., savedir=..., run_opts={...})`.\n- Audio tensors generally follow batch-time-channel conventions. Mono waveforms are often `(batch, time)`; multi-channel waveforms use an extra channel dimension.\n- CPU is enough for imports, small fixtures, and many debug examples. Full recipe training and profiling often need CUDA or another accelerator; do not treat a CPU smoke check as proof of GPU throughput.\n\n## Evidence, provenance, and routing metadata\n\n- Read `references\u002Frepo-provenance.md` before checking staleness or refreshing this skill.\n- `references\u002Frepo-routing-metadata.json` contains structured router metadata for managed repo-skill import tooling.\n- This runtime skill is self-contained. It does not require opening the original SpeechBrain checkout; source-relative evidence paths appear only in provenance and review artifacts.\n","# SpeechBrain repo skill\n\nUse this skill when a task involves the SpeechBrain Python package, SpeechBrain recipes, pretrained SpeechBrain models, HyperPyYAML experiment files, audio\u002Fdata pipelines, speech preprocessing, speech metrics, or maintaining the SpeechBrain repository.\n\nSpeechBrain is a PyTorch-based speech and conversational-AI toolkit. It exposes both a library (`speechbrain`) and a large recipe collection. Start here to choose the right focused route, then read only the linked sub-skill\u002Freference needed for the task.\n\n## Quick install and import check\n\nFor ordinary package use:\n\n```bash\npip install speechbrain\npython - \u003C\u003C'PY'\nimport speechbrain as sb\nprint(sb.__version__)\nprint(sb.Brain)\nPY\n```\n\nFor local recipe development from a source checkout, install the repository and its dependencies in an isolated environment:\n\n```bash\npip install -r requirements.txt\npip install --editable .\npython -m pip check\n```\n\nRun the bundled environment smoke script when diagnosing setup or optional dependency issues:\n\n```bash\npython scripts\u002Fcheck_speechbrain_install.py --json\n```\n\nRead `references\u002Finstallation-and-environment.md` for dependency, Python\u002FTorch, audio backend, Hugging Face, and CPU\u002FGPU notes. Read `references\u002Ftroubleshooting.md` for cross-cutting install, import, audio, network\u002Fcache, and runtime failures.\n\n## Route map\n\n| User task | Read |\n| --- | --- |\n| Use pretrained models for ASR, speaker verification, classification, enhancement, separation, VAD, TTS, G2P, or local\u002FHugging Face model loading. | `sub-skills\u002Fpretrained-inference\u002FSKILL.md` |\n| Run or adapt a recipe, create a new recipe from templates, debug HyperPyYAML overrides, use `Brain`, or launch CPU\u002FGPU\u002FDDP training. | `sub-skills\u002Frecipe-training\u002FSKILL.md` |\n| Load\u002Fsave audio, build `DynamicItemDataset`\u002F`DataPipeline`, train tokenizers, create audio features, apply augmentation, beamforming, or vocal-feature preprocessing. | `sub-skills\u002Fdata-audio-pipelines\u002FSKILL.md` |\n| Choose neural blocks, decoders, losses, metric stats, WER scoring, checkpoint recovery, `Pretrainer`, streaming helpers, or component-level tests. | `sub-skills\u002Fcomponents-metrics\u002FSKILL.md` |\n| Maintain the repository: focused tests, recipe CSV consistency, docs generation, performance tables, lint\u002Fpre-commit, or contributor review checks. | `sub-skills\u002Frepo-maintenance\u002FSKILL.md` |\n\n## Working model\n\n- SpeechBrain experiments are usually a Python script plus a HyperPyYAML file: `python train.py hparams.yaml --override value`.\n- `speechbrain.Brain` owns train\u002Fvalid\u002Ftest loops; recipes subclass it and override forward\u002Fobjective hooks.\n- Pretrained inference classes inherit `speechbrain.inference.interfaces.Pretrained` and are commonly loaded with `Class.from_hparams(source=..., savedir=..., run_opts={...})`.\n- Audio tensors generally follow batch-time-channel conventions. Mono waveforms are often `(batch, time)`; multi-channel waveforms use an extra channel dimension.\n- CPU is enough for imports, small fixtures, and many debug examples. Full recipe training and profiling often need CUDA or another accelerator; do not treat a CPU smoke check as proof of GPU throughput.\n\n## Evidence, provenance, and routing metadata\n\n- Read `references\u002Frepo-provenance.md` before checking staleness or refreshing this skill.\n- `references\u002Frepo-routing-metadata.json` contains structured router metadata for managed repo-skill import tooling.\n- This runtime skill is self-contained. It does not require opening the original SpeechBrain checkout; source-relative evidence paths appear only in provenance and review artifacts.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fspeechbrain",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill speechbrain",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill speechbrain",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill speechbrain","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspeechbrain\u002FSKILL.md",[47,53,57,61,65],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Finstallation-and-environment.md","REFERENCE","参考文档",4509,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspeechbrain\u002Freferences\u002Finstallation-and-environment.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Frepo-provenance.md",2792,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspeechbrain\u002Freferences\u002Frepo-provenance.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Frepo-routing-metadata.json",502,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspeechbrain\u002Freferences\u002Frepo-routing-metadata.json",{"path":62,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":63,"sourceHtmlUrl":64},"references\u002Ftroubleshooting.md",4786,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspeechbrain\u002Freferences\u002Ftroubleshooting.md",{"path":66,"resourceType":67,"resourceTypeDesc":68,"sizeBytes":69,"sourceHtmlUrl":70},"scripts\u002Fcheck_speechbrain_install.py","SCRIPT","脚本",3829,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fspeechbrain\u002Fscripts\u002Fcheck_speechbrain_install.py",[72,79,86,93,100,107],{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]