协作头脑风暴
brainstorming
在实现前澄清需求、探索设计选择,并形成清晰的开发方向。
local-v15-streaming【开发与工程】Operate MOSS-TTS Local Transformer v1.5 batch and realtime streaming decode workflows.
独立 GitHub 快照 · 自动分类 · 以原作者文档为准
Use this sub-skill when the task is about MOSS-TTS-Local-Transformer-v1.5 local batch inference, realtime streaming decode, browser streaming app operation, 48 kHz stereo codec-v2 audio, device/dtype split, token or duration estimates, continuation prompts, or voice-clone prompts.
../realtime-voice-agent/SKILL.md.../hf-family-workflows/SKILL.md.../finetuning-data-prep/SKILL.md.../soundeffect-v2/SKILL.md.OpenMOSS-Team/MOSS-TTS-Local-Transformer-v1.5.OpenMOSS-Team/MOSS-Audio-Tokenizer-v2.[2, samples].1.7, top-p 0.8, top-k 25, repetition penalty 1.0.references/batch-and-streaming.md.references/api-reference.md.references/troubleshooting.md.scripts/estimate_local_v15_tokens.py.Before claiming a v1.5 workflow is correct, verify that the runtime reports the expected sample rate (48000), RVQ depth (12), and stereo channel count, and that final output includes a WAV, audio-token dump, and metadata JSON in the configured output location.