Skip to content

Deploy Silero VAD on Alif Ensemble E8 with ExecuTorch - #4024

Open
usamahz wants to merge 3 commits into
ArmDeveloperEcosystem:mainfrom
usamahz:codex/silero-alif-learning-path
Open

usamahz wants to merge 3 commits into
ArmDeveloperEcosystem:mainfrom
usamahz:codex/silero-alif-learning-path

Conversation

@usamahz

@usamahz usamahz commented Nov 6, 2026 •

Copy link
Copy Markdown
Contributor

Add a Learning Path for live Silero VAD on the Alif Ensemble E8 A0, using the on-board microphone, Cortex-M55 HP core, Ethos-U85, and a 480 × 800 dashboard. A separate build validates a deterministic 79-window recording against its host reference before switching to live input. The path includes released dependencies, pinned board support, application sources, and probe-selected programming with fresh MRAM readbacks.

Both firmware configurations cross-built. The physical deterministic run passed all 79 windows with zero threshold-decision mismatches and maximum absolute probability error 4.70 × 10⁻⁷ against rounded UART output; the original tolerances are unchanged. Fresh firmware and signed-package readbacks passed for both modes.

The live acoustic run covered 49.152 seconds at the expected 16 kHz cadence, with speech/quiet response, at most two of eight capture slabs occupied, and no reported errors. The restored live image also passed a separate 20-second reset capture. These sparse observations establish functional response, not an accuracy benchmark. The controlled acoustic interval added no PCM-rail clips to its initial count of 36; the separate final reset increased its count from 38 to 41. The dashboard screenshot is an actual target framebuffer readback with register checks; physical panel updates have not been manually confirmed.

All 15 packaged files match the final source. Nine Markdown pages, 30 Bash blocks, five embedded Python snippets, focused Hugo rendering, and lesson/asset links were checked. Both configurations were built from the packaged sources; the only subsequent archive change was its README.

Authored with assistance from OpenAI Codex.

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the Creative Commons Attribution 4.0 International License.

Authored with assistance from OpenAI Codex.
Document the tested microphone dashboard, deterministic reference validation, and verified board programming workflow, including observed limits.

Authored with assistance from OpenAI Codex.
@usamahz
usamahz marked this pull request as ready for review November 18, 2026 14:50
Align the Silero Learning Path metadata with the upstream category validator.

Authored with assistance from OpenAI Codex.
@usamahz
usamahz force-pushed the codex/silero-alif-learning-path branch from 053356c to 32ccdd1 Compare November 18, 2026 15:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant