feat: 3-mode selfhosted refactoring (--gpu, --cpu, --hosted) + audio token auth fallback (#896)

* fix: local processing instead of http server for cpu

* add fallback token if service worker doesnt work

* chore: rename processors to keep processor pattern up to date and allow other processors to be createed and used with env vars
This commit is contained in:
Juan Diego García
2026-03-04 16:31:08 -05:00
committed by GitHub
parent 4235ab4293
commit a682846645
34 changed files with 2640 additions and 172 deletions

View File

@@ -254,15 +254,15 @@ Reflector can run completely offline:
Control where each step happens:
```yaml
# All local processing
TRANSCRIPT_BACKEND=local
DIARIZATION_BACKEND=local
TRANSLATION_BACKEND=local
# All in-process processing
TRANSCRIPT_BACKEND=whisper
DIARIZATION_BACKEND=pyannote
TRANSLATION_BACKEND=marian
# Hybrid approach
TRANSCRIPT_BACKEND=modal # Fast GPU processing
DIARIZATION_BACKEND=local # Sensitive speaker data
TRANSLATION_BACKEND=modal # Non-sensitive translation
TRANSCRIPT_BACKEND=modal # Fast GPU processing
DIARIZATION_BACKEND=pyannote # Sensitive speaker data
TRANSLATION_BACKEND=modal # Non-sensitive translation
```
### Storage Options