ai-service

Author	SHA1	Message	Date
Grendgi	bde56978d6	Fix Whisper large v3 audio compose Some checks failed CI / test (push) Failing after 8s Details Build and Deploy / build-and-deploy (push) Successful in 18s Details	2026-06-10 10:15:24 +03:00
Grendgi	8d6cd84403	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	2026-06-10 10:10:13 +03:00
Grendgi	9bd6d726f0	Make Voxtral the only transcription provider Some checks failed CI / test (push) Failing after 8s Details Build and Deploy / build-and-deploy (push) Successful in 27s Details	2026-06-09 16:54:54 +03:00
Grendgi	94e0d03580	Switch transcription comparison to Voxtral All checks were successful CI / test (push) Successful in 13s Details Build and Deploy / build-and-deploy (push) Successful in 18s Details	2026-06-09 15:11:52 +03:00
Grendgi	2ef71a822b	Add vLLM audio image for transcription models All checks were successful CI / test (push) Successful in 13s Details Build and Deploy / build-and-deploy (push) Successful in 22s Details	2026-06-09 13:38:08 +03:00
Grendgi	ee6e948d2e	Add single WhisperX load balancer config	2026-06-09 13:20:17 +03:00
Grendgi	e132634c65	Isolate audio model compose network	2026-06-09 13:17:05 +03:00
Grendgi	cac8d89e64	Tune audio model GPU profiles	2026-06-09 12:52:13 +03:00
Grendgi	f49ba7abd5	Add AI server audio model profiles	2026-06-09 12:50:56 +03:00