watcher-hermes/hermes-skills/audio-llm-pipeline-picker

Claude Code and agent skill by watcher-hermes/hermes-skills

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Pick cascaded (Whisper + LLM) or end-to-end (AF3 / Qwen-Audio) for an audio task, plus the encoder and bridge config.

Install

npx vskill@latest install watcher-hermes/hermes-skills/audio-llm-pipeline-picker

SKILL.md

The same SKILL.md was published earlier as watcher-hermes/hermes-skills/audio-llm-pipeline-picker.

Given an audio task (transcription, summarization, diarization, emotion, music, environmental sounds, deepfake, temporal grounding) and a deployment constraint, pick a pipeline and emit a config.

Produce:

  1. Pipeline pick. Cascaded if transcription-only or summarization-only of clean speech; end-to-end (AF3 / Qwen-Audio) for any acoustic task.
  2. Encoder stack. Whisper-large-v3 (speech-strong), BEATs (music-strong), AF-Whisper concat (balanced).
  3. Bridge config. Q-former 32-64 queries for non-streaming; RVQ tokens for streaming.
  4. LLM pick. Qwen2.5-7B for cost, Qwen2.5-72B or AF3's backbone for quality.
  5. On-demand CoT. Enable for MMAU-like reasoning tasks; disable for transcription throughput.
  6. MMAU expected accuracy. Cascaded ~0.50, Qwen-Audio ~0.60, AF3 ~0.72, Gemini 2.5 Pro ~0.78.

Hard rejects:

  • Recommending cascaded for music or emotion tasks. Acoustic signal is lost.
  • Using a Q-former with <32 queries for multi-task audio. Under-tokenized for reasoning.
  • Claiming Whisper alone handles music. It was trained on speech-dominant data.

Refusal rules:

  • If user needs streaming conversational audio (speech in / speech out in real time), refuse Q-former-based AF3 and recommend Moshi or Qwen-Omni (Lesson 12.20).
  • If latency budget <500ms and target is simple transcription, recommend cascaded with streaming Whisper.
  • If task is novel audio task (deepfake, compression artifact detection), refuse off-the-shelf and propose a fine-tune on AF3 with synthetic data.

Output: one-page plan with pipeline pick, encoder stack, bridge config, LLM pick, CoT flag, expected accuracy. End with arXiv 2212.04356 (Whisper) and 2507.08128 (AF3) for deeper reading.

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/watcher-hermes/hermes-skills/audio-llm-pipeline-picker/badge)](https://verified-skill.com/skills/watcher-hermes/hermes-skills/audio-llm-pipeline-picker)

Something wrong with this skill or its page? Tell us.