deploy standalone ASR pipeline on tools-pve

2026-09-18 02:32:14 -07:00
parent f30f72b295
commit b23f00f41a
38 changed files with 182773 additions and 0 deletions
@@ -0,0 +1,34 @@
+from __future__ import annotations
+
+import os
+from pathlib import Path
+
+DATA = Path(os.getenv("ASR_DATA_DIR", "/data"))
+INBOX = DATA / "inbox"
+PROCESSING = DATA / "processing"
+PROCESSED = DATA / "processed"
+FAILED = DATA / "failed"
+TRANSCRIPTS = DATA / "transcripts"
+STATE = Path(os.getenv("ASR_STATE_DIR", "/state"))
+DRAFTS = DATA / "artifacts" / "drafts"
+RESULTS = DATA / "artifacts" / "results"
+LOGS = DATA / "logs"
+META = STATE / "uploads"
+REVISION_QUEUE = STATE / "revision-queue"
+DB = STATE / "intake.db"
+SUPPORTED = {".m4a", ".mp3", ".wav", ".mp4", ".aac", ".ogg", ".opus", ".webm", ".flac"}
+PUBLIC_URL = os.getenv("ASR_PUBLIC_URL", "http://192.168.50.49:8788").rstrip("/")
+AGENT_TOKEN = os.getenv("ASR_AGENT_TOKEN", "")
+DIARIZE_URL = os.getenv("ASR_DIARIZE_URL", "http://192.168.50.100:10099/asr")
+MAX_UPLOAD = int(os.getenv("ASR_UPLOAD_MAX_BYTES", str(4 * 1024**3)))
+POLL_SECONDS = max(1, int(os.getenv("ASR_POLL_SECONDS", "5")))
+STABLE_SECONDS = max(1, int(os.getenv("ASR_STABLE_SECONDS", "10")))
+MAX_ATTEMPTS = max(1, int(os.getenv("ASR_MAX_ATTEMPTS", "3")))
+
+
+def ensure_dirs() -> None:
+    for path in (INBOX, PROCESSING, PROCESSED, FAILED, TRANSCRIPTS, DRAFTS,
+                 RESULTS, STATE, LOGS, META, REVISION_QUEUE, DATA / "cache",
+                 DATA / "artifacts" / "raw", DATA / "vault" / "minutes",
+                 DATA / "vault" / "People", DATA / "vault" / "Companies"):
+        path.mkdir(parents=True, exist_ok=True)