Hidosi/umb
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: preload Whisper model at startup with disk space check

Browse Source 
- Add WHISPER_MODEL_SIZE and WHISPER_MIN_FREE_SPACE_BYTES config options
- voice.py now preloads/downloads the Whisper model at bot startup
- Detailed logging for model presence, disk space, download progress and readiness
- If model is already present locally, preload is skipped
- If disk space is insufficient, bot fails fast with a clear error
- main.py calls preload_model() after proxy setup and before polling
- Document voice recognition model download behavior in README
This commit is contained in:
Галингер Р.С.
2026-07-08 09:44:48 +07:00
parent 0432155c8f
commit d6c029f708
4 changed files with 137 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
config.py
+5
View File
@@ -28,6 +28,11 @@ AI_BLOCK_DEFAULT_DURATION = 86400
AI_HEALTH_CHECK_ENABLED = os.getenv("AI_HEALTH_CHECK_ENABLED", "false").lower() == "true"
AI_HEALTH_CHECK_INTERVAL = int(os.getenv("AI_HEALTH_CHECK_INTERVAL", "600"))
# Whisper model settings.
# The base model requires ~2.5 GB for download; 5 GB free space is recommended.
WHISPER_MODEL_SIZE = os.getenv("WHISPER_MODEL_SIZE", "base")
WHISPER_MIN_FREE_SPACE_BYTES = int(os.getenv("WHISPER_MIN_FREE_SPACE_BYTES", str(5 * 1024 * 1024 * 1024)))
ACCESS_KEY = os.getenv("ACCESS_KEY", "").strip()
SECRET_KEY = os.getenv("SECRET_KEY", "").strip()
BUCKET_NAME = os.getenv("BUCKET_NAME", "").strip()