[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795YD2CZH1RYDF9Z2R5WS8P":3,"skill-same:01M795YD2CZH1RYDF9Z2R5WS8P":70},{"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":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M795YD2CZH1RYDF9Z2R5WS8P","training",null,"Guides Tacotron training command construction, hyperparameter overrides, data-feeder contracts, logs, checkpoints, TensorBoard, restore runs, and loss troubleshooting.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftacotron\u002Fsub-skills\u002Ftraining\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: training\ndescription: \"Guides Tacotron training command construction, hyperparameter\n  overrides, data-feeder contracts, logs, checkpoints, TensorBoard, restore\n  runs, and loss troubleshooting.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Training\n\nUse this route for training a Tacotron model, preparing a restore run, changing\nhparams, interpreting logs\u002Fcheckpoints, or planning resource requirements. Full\ntraining is long-running and data-dependent; build and validate the command\nbefore launching it.\n\n## Workflow\n\n1. Complete the data-preparation route and validate `training\u002Ftrain.txt`.\n2. Choose a stable `--base_dir`, `--input`, and `--name`. The default log\n   directory is `\u003Cbase_dir>\u002Flogs-\u003Cname-or-model>`.\n3. Pass hparam overrides as comma-separated `name=value` pairs. Preserve the\n   same audio\u002Fmodel hparams for evaluation and serving.\n4. Use `--restore_step N` only when `\u003Clog_dir>\u002Fmodel.ckpt-N` exists. Use\n   `--git` only in a clean source checkout; it intentionally fails on dirty\n   state.\n5. Monitor summaries, generated audio, and alignments. If loss explodes or\n   attention is lost, stop safely and consider restoring before the spike.\n## Command roots and training boundary\n\nBuild commands from the skill root; execute the printed command only from the\nTacotron checkout root. The input and output paths remain relative to the\nselected `--base-dir`, not to the skill directory.\n\n```bash\nSKILL_ROOT=\u002Fpath\u002Fto\u002Ftacotron-skill\nCHECKOUT_ROOT=\u002Fpath\u002Fto\u002Ftacotron-checkout\ncd \"$SKILL_ROOT\" && python sub-skills\u002Ftraining\u002Fscripts\u002Fbuild_train_command.py --checkout-root \"$CHECKOUT_ROOT\" --base-dir \u002Fdata\u002Ftacotron --input training\u002Ftrain.txt --hparams batch_size=16,max_iters=300\n```\n\nThe builder is dry-run only. Actual training requires validated metadata,\ndecoded\u002Fpreprocessed audio arrays, the compatible TensorFlow 1.x stack, disk,\nmemory, and potentially GPU resources; it may write checkpoints, WAV samples,\nalignments, and logs. No training convergence or checkpoint restore is implied\nby command construction or metadata validation.\n\nRead [`references\u002Fcli-reference.md`](references\u002Fcli-reference.md) for flags,\n[`references\u002Fhparams.md`](references\u002Fhparams.md) for defaults and duration\ncalculations, [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for a safe\nsequence, and [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\nfor data, loss, and restore failures. Use\n[`scripts\u002Fbuild_train_command.py`](scripts\u002Fbuild_train_command.py) to construct\ncommands without starting a training loop.\n","# Training\n\nUse this route for training a Tacotron model, preparing a restore run, changing\nhparams, interpreting logs\u002Fcheckpoints, or planning resource requirements. Full\ntraining is long-running and data-dependent; build and validate the command\nbefore launching it.\n\n## Workflow\n\n1. Complete the data-preparation route and validate `training\u002Ftrain.txt`.\n2. Choose a stable `--base_dir`, `--input`, and `--name`. The default log\n   directory is `\u003Cbase_dir>\u002Flogs-\u003Cname-or-model>`.\n3. Pass hparam overrides as comma-separated `name=value` pairs. Preserve the\n   same audio\u002Fmodel hparams for evaluation and serving.\n4. Use `--restore_step N` only when `\u003Clog_dir>\u002Fmodel.ckpt-N` exists. Use\n   `--git` only in a clean source checkout; it intentionally fails on dirty\n   state.\n5. Monitor summaries, generated audio, and alignments. If loss explodes or\n   attention is lost, stop safely and consider restoring before the spike.\n## Command roots and training boundary\n\nBuild commands from the skill root; execute the printed command only from the\nTacotron checkout root. The input and output paths remain relative to the\nselected `--base-dir`, not to the skill directory.\n\n```bash\nSKILL_ROOT=\u002Fpath\u002Fto\u002Ftacotron-skill\nCHECKOUT_ROOT=\u002Fpath\u002Fto\u002Ftacotron-checkout\ncd \"$SKILL_ROOT\" && python sub-skills\u002Ftraining\u002Fscripts\u002Fbuild_train_command.py --checkout-root \"$CHECKOUT_ROOT\" --base-dir \u002Fdata\u002Ftacotron --input training\u002Ftrain.txt --hparams batch_size=16,max_iters=300\n```\n\nThe builder is dry-run only. Actual training requires validated metadata,\ndecoded\u002Fpreprocessed audio arrays, the compatible TensorFlow 1.x stack, disk,\nmemory, and potentially GPU resources; it may write checkpoints, WAV samples,\nalignments, and logs. No training convergence or checkpoint restore is implied\nby command construction or metadata validation.\n\nRead [`references\u002Fcli-reference.md`](references\u002Fcli-reference.md) for flags,\n[`references\u002Fhparams.md`](references\u002Fhparams.md) for defaults and duration\ncalculations, [`references\u002Fworkflows.md`](references\u002Fworkflows.md) for a safe\nsequence, and [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\nfor data, loss, and restore failures. Use\n[`scripts\u002Fbuild_train_command.py`](scripts\u002Fbuild_train_command.py) to construct\ncommands without starting a training loop.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Ftacotron\u002Fsub-skills\u002Ftraining",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill training",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill training",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill training","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftacotron\u002Fsub-skills\u002Ftraining\u002FSKILL.md",[46,52,56,60,64],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fcli-reference.md","REFERENCE","参考文档",1134,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftacotron\u002Fsub-skills\u002Ftraining\u002Freferences\u002Fcli-reference.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Fhparams.md",1020,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftacotron\u002Fsub-skills\u002Ftraining\u002Freferences\u002Fhparams.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",1280,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftacotron\u002Fsub-skills\u002Ftraining\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":62,"sourceHtmlUrl":63},"references\u002Fworkflows.md",1625,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftacotron\u002Fsub-skills\u002Ftraining\u002Freferences\u002Fworkflows.md",{"path":65,"resourceType":66,"resourceTypeDesc":67,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Fbuild_train_command.py","SCRIPT","脚本",2325,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Ftacotron\u002Fsub-skills\u002Ftraining\u002Fscripts\u002Fbuild_train_command.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"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.","Apache-2.0","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":75,"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":75,"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":75,"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":75,"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":75,"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",[],[]]