docs(homelab): the engine timeout, a local chat model, ffmpeg in the image, and 31B with Low Power Mode off
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -23,15 +23,13 @@ it** — endpoints and aliases drift, and this file is a snapshot (2026-06-06),
|
|||||||
`{"error":"failed to process audio"}` string — it has had at least five causes. Tapir's knobs:
|
`{"error":"failed to process audio"}` string — it has had at least five causes. Tapir's knobs:
|
||||||
`TAPIR_UPLOADS_ENABLED` (off by default), `TAPIR_UPLOAD_MAX_MB` (200), `TAPIR_UPLOAD_MAX_MINUTES`
|
`TAPIR_UPLOADS_ENABLED` (off by default), `TAPIR_UPLOAD_MAX_MB` (200), `TAPIR_UPLOAD_MAX_MINUTES`
|
||||||
(90), `TAPIR_TRANSCRIBE_MODEL`, `TAPIR_TRANSCRIBE_FALLBACK_MODEL` (empty disables the cloud
|
(90), `TAPIR_TRANSCRIBE_MODEL`, `TAPIR_TRANSCRIBE_FALLBACK_MODEL` (empty disables the cloud
|
||||||
fallback), `TAPIR_TRANSCRIBE_TIMEOUT` (30m), `TAPIR_UPLOAD_TMP_DIR`, `TAPIR_FFMPEG_BIN`,
|
fallback), `TAPIR_TRANSCRIBE_TIMEOUT` (60m, the whole job), `TAPIR_TRANSCRIBE_ENGINE_TIMEOUT` (25m, one engine call: a wedged engine then fails while the job lives and the fallback can run), `TAPIR_UPLOAD_TMP_DIR`, `TAPIR_FFMPEG_BIN`,
|
||||||
`TAPIR_FFPROBE_BIN`, `TAPIR_MAX_UPLOADED_TRANSCRIPT_CHARS` (90000 — the measured ceiling of
|
`TAPIR_FFPROBE_BIN`, `TAPIR_MAX_UPLOADED_TRANSCRIPT_CHARS` (90000 — the measured ceiling of
|
||||||
`iguana/gemma4-26b`, which silently drops the head above it), `TAPIR_UPLOAD_CHAT_MODEL`
|
`iguana/gemma4-26b`, which silently drops the head above it), `TAPIR_UPLOAD_CHAT_MODEL`
|
||||||
(`iguana/gemma4-26b`; `koala/phi4-mini`'s 8,192-token context 400s on an hour of speech). Needs `ffmpeg` + `ffprobe`
|
(`iguana/gemma4-26b`; must be a local `koala/` or `iguana/` alias, since the whole private transcript is sent to it; `koala/phi4-mini`'s 8,192-token context 400s on an hour of speech). `ffmpeg` + `ffprobe` are in the runtime image (static, pinned by sha256; #34 decided A on 2026-10-02); Tapir's own ingress body limit for a 200 MB upload is unverified (infra).
|
||||||
in the runtime image; Tapir's own ingress body limit for a 200 MB upload is unverified (infra).
|
|
||||||
**Two-engine mode (ADR-034), off unless `TAPIR_RECONCILE_BASE_MODEL` is set:** it runs
|
**Two-engine mode (ADR-034), off unless `TAPIR_RECONCILE_BASE_MODEL` is set:** it runs
|
||||||
`iguana/pianissimo` (the base text) and `TAPIR_TRANSCRIBE_MODEL` (kb-whisper) on the same audio, then a
|
`iguana/pianissimo` (the base text) and `TAPIR_TRANSCRIBE_MODEL` (kb-whisper) on the same audio, then a
|
||||||
LOCAL chat model (`TAPIR_RECONCILE_MODEL`, e.g. `iguana/gemma4-26b`: 92% against a speaker's blind answers
|
LOCAL chat model (`TAPIR_RECONCILE_MODEL`) chooses between their disagreements. **Deployment choice (2026-10-02): `iguana/gemma4-31b`** (97% against a speaker's blind answers; 92% for `iguana/gemma4-26b`). With iguana's macOS **Low Power Mode off** the 31B decodes at 22 tok/s and reconciled a 63.6-minute recording in 21 min 49 s end to end; with it on it ran at 8 tok/s. Check `pmset -g | grep lowpowermode` before blaming a model or an engine for slowness.
|
||||||
at ~2 s a call; `iguana/gemma4-31b` 97% but ~5x slower) chooses between their disagreements.
|
|
||||||
`TAPIR_RECONCILE_CHECK_ORDER=true` asks twice per dispute with the order swapped (doubles the time).
|
`TAPIR_RECONCILE_CHECK_ORDER=true` asks twice per dispute with the order swapped (doubles the time).
|
||||||
Every model must start `koala/` or `iguana/`: a cloud alias is a start-up error. The default job timeout is
|
Every model must start `koala/` or `iguana/`: a cloud alias is a start-up error. The default job timeout is
|
||||||
60 minutes. `iguana/pianissimo` is KlangAI's Swedish ASR (a Parakeet/FastConformer on MLX, served by a small
|
60 minutes. `iguana/pianissimo` is KlangAI's Swedish ASR (a Parakeet/FastConformer on MLX, served by a small
|
||||||
|
|||||||
Reference in New Issue
Block a user