Kavin

What an agent can do with the SoundSight corpus

ran-nope/SoundSight: Environmental sound classification with ESC-50, reproducible ML evaluation, and a Streamlit audio upload demo

• Look up how SoundSight implements audio-classification, esc-50, mfcc, with answers cited to file and line.
• Reuse a worked example: the commit “Add reproducible audio ML package” (5 files · Python).
• Answer from SoundSight's real Python source instead of memory (AI, prompts and agents).

• Where does SoundSight handle “Add reproducible audio ML package”?
• How does SoundSight implement audio-classification?
• What does src/soundsight do in SoundSight?

Search the GitHub repository ran-nope/SoundSight with XERJ (https://hub.xerj.org/corpus/ran-nope--soundsight).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/ran-nope/SoundSight SoundSight && git -C SoundSight checkout 4c65aa87b71a23177e9895608dce1abbdc3756a9
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./SoundSight --url http://127.0.0.1:9200 --prefix soundsight --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: MIT. Keep the copyright notice and credit the authors.

corpus ran-nope--soundsight · AI, prompts and agents
Related corpora: DeltaN04/rul-turbofan-Jet-Engine, ArianShayestehfard/Watchlist-Decision-Engine
AI search and retrieval with XERJ · Case study: reference coding for agents