admin/ai-service
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Switch transcription to Whisper large v3
Some checks failed
CI / test (push) Failing after 10s
Details
Build and Deploy / build-and-deploy (push) Successful in 24s
Details

Browse Source
This commit is contained in:
Grendgi
2026-06-10 10:10:13 +03:00
parent 1b63dcdbf5
commit 8d6cd84403
12 changed files with 85 additions and 93 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
k8s/configmap.yaml
View File

@@ -11,11 +11,11 @@ data:
LLM_BASE_URL: "http://10.2.3.5:8002"
LLM_MODEL: "qwen2.5-14b"
LLM_TIMEOUT: "5m"
# Voxtral Small is the only transcription provider. It is exposed on the AI
# server through an OpenAI-compatible /v1/audio/transcriptions endpoint.
VOXTRAL_BASE_URL: "http://10.2.3.5:8004"
VOXTRAL_MODEL: "mistralai/Voxtral-Small-24B-2507"
VOXTRAL_TIMEOUT: "30m"
# Whisper Large v3 is exposed on the AI server through an OpenAI-compatible
# /v1/audio/transcriptions endpoint.
AUDIO_TRANSCRIPTION_BASE_URL: "http://10.2.3.5:8004"
AUDIO_TRANSCRIPTION_MODEL: "openai/whisper-large-v3"
AUDIO_TRANSCRIPTION_TIMEOUT: "30m"
AI_STATS_SIDECAR_URL: "http://10.2.3.5:9090"
AI_STATS_TIMEOUT: "8s"
WORKER_POLL_INTERVAL: "2s"