Files

T

Keysat 9ef9226e0a docs: split CLAUDE.md into path-scoped .claude/rules; fix dev/test commands

- CLAUDE.md trimmed to whole-repo facts (58 lines); subsystem guidance
  moved to .claude/rules/{startos-package,fastapi-image,redaction,
  audio-speech}.md with paths: frontmatter so each loads only when
  matching files are touched
- .gitignore: track .claude/rules/ while keeping the rest of .claude/
  (settings.local.json) ignored
- test-audio-with-speakers.sh: require audio-file arg in docs, replace
  owner-specific SPARK_CONTROL/VLLM defaults with generic ones
  (localhost dev server + Spark Control vLLM proxy), discover the
  loaded LLM via /api/status since /v1/models lists audio models only
- document REDACTION_MAP_DB + CONNECTIVITY_LOG as required for local
  dev (/data only exists in the container)
- prettier pass over startos/actions (formatting drift)

2026-06-11 19:12:23 -05:00

2.1 KiB

Raw Blame History

paths

image/app/audio_proxy.py

image/app/speech_models.py

image/app/deep_health.py

image/parakeet_patches/**

scripts/test-audio-with-speakers.sh

docs/AUDIO_API.md

Audio / speech stack (Parakeet STT + Sortformer diarizer + Kokoro TTS on Spark 2)

Changing the parakeet-asr container

image/parakeet_patches/ (main.py, diarizer.py) is an overlay copied into the parakeet-asr container by the "Reapply speech-model patches" dashboard action (image/app/speech_models.py). This is the only durable way to change that container — docker exec / pip changes inside it die on docker rm.
Never install cuda-python in parakeet-asr to "fix" the startup warning about CUDA graphs being disabled. The warning is harmless; enabling the graph path crashes real decode with illegal memory access on this GPU/CUDA-13 stack (GB10/sm_121). The slow path served 11k+ requests with zero failures — leave it alone.
Pin/constrain torch versions when pip-installing anything into NGC-based containers on the Sparks (ABI breaks otherwise); expect ARM64 wheel gaps and source builds (--no-build-isolation for torchaudio). Applies to spark_embed too.

Testing audio endpoints

Test with real speech (e.g. say -o /tmp/t.wav --data-format=LEI16@16000 "<a couple of sentences>"), not tones/silence — zero-token audio skips the decoder paths where crashes live.
Send audio requests to Spark 2 sequentially in tests/scripts. Parallel audio requests can race (cuFFT → 503), and the single GPU serializes them anyway.
End-to-end suite (hits the LIVE cluster):

./scripts/test-audio-with-speakers.sh <audio-file>   # from repo root

SPARK_CONTROL defaults to http://127.0.0.1:9999 (a running local dev server); point it at the installed package URL otherwise.

API quirk

Spark Control's /v1/models lists audio models (STT model + Kokoro voices) by design — not the loaded LLM. Discover the LLM via /api/status (vllm.current_model).

Diarizer caps at 4 speakers (Sortformer diar_sortformer_4spk-v1).

2.1 KiB Raw Blame History

Audio / speech stack (Parakeet STT + Sortformer diarizer + Kokoro TTS on Spark 2)

Changing the parakeet-asr container

Testing audio endpoints

API quirk

2.1 KiB

Raw Blame History