wb aae53d91b1 fix(diarization-ui): prevent repetition loops in Ollama generation ...

Adds repeat_penalty=1.15 and repeat_last_n=128 to suppress token
repetition loops (e.g. "tragen" -> "tragen" -> ...). Also caps output
via num_predict (default 4096, configurable via OLLAMA_NUM_PREDICT env
var) as a hard stop in case the model still gets stuck.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-05-06 16:04:12 +02:00

136 B

Raw Blame History

View Raw