docs(scriberr): saved GPU+speaker profiles; first diarized job after the fixes

2026-10-06 13:36:31 -07:00
parent ec888c3130
commit efd31b4ef1
2 changed files with 3 additions and 1 deletions
@@ -144,6 +144,8 @@ Prime: "whisper doesn't work at all, and I need diarized transcripts." There wer

 **Re-verified with the placeholder token and the /tank cache (60 s clip): community-1 exited 0 in 8 s, WhisperX+3.1 exited 0 in 28 s, both 2 speakers, with no downloads and no 401s.** First verification, with the real token, on a 4-min multi-speaker clip of a real upload, GPU 3: WhisperX large-v3/cuda/float16 + `pyannote/speaker-diarization-3.1` exited 0 in 65 s with 2 speakers. The pyannote env script with `speaker-diarization-community-1` (the adapter's only option, used by the Parakeet profile) exited 0 in 11 s with 3 speakers. The two pipelines disagree on the speaker count, so set min/max speakers when you know it. WhisperX's own env (pyannote.audio 4.0.4) loads 3.1 fine and feeds the pipeline in-memory audio, so it never needed torchcodec.

+**Saved profiles (Prime, 2026-10-06):** `WhisperX large-v3 · GPU · speakers` (whisper, large-v3, cuda, float16, batch 16, pyannote 3.1) and `Parakeet · GPU · speakers` (Parakeet TDT 0.6B, English, pyannote community-1). Both were inserted straight into `transcription_profiles` as uid 10001, with no restart. Backup: `/tank/scriberr/data/scriberr.db.bak-20261006-profiles`. The older `ParakeetEng` profile was left as it was. **First real job after the fixes:** Prime's 1-hour upload with Parakeet + pyannote finished in 3m30s (transcription 46 s, 11,985 words; diarization 2m38s, 3 speakers).
+
 ## Optional: summarisation via the LiteLLM gateway

 Scriberr speaks the OpenAI API, so point it at the fleet gateway instead of a