feat(tools-pve/asr-pipeline): multi-backend ASR web app with LiteLLM routing

servers/tools-pve/asr-pipeline/asrpipe/segment.py

@@ -22,6 +22,7 @@ import re
 from dataclasses import dataclass, field
 
 VOICEPRINT_HDR = re.compile(r"^<!--\s*voiceprint_session:")
+PROVIDER_HDR = re.compile(r"^<!--\s*asr_provider:\s*(\S+)(?:\s+model:\s*(\S+))?\s*-->")
 SEGMENT_BANNER = re.compile(r"^---\s*第\d+段.*---\s*$")
 TURN_TAG = re.compile(r"^【([^】]+)】\s*(.*)$", re.S)
 VIBE_TAG = re.compile(r"^\[(\d{1,2}:\d{2})\]\s*(S\d+)\s*[:：]\s*(.*)$", re.S)
@@ -95,6 +96,11 @@ class Chunk:
 
 def detect_backend(raw: str) -> str:
     head = raw[:500]
+    m_prov = PROVIDER_HDR.search(head)
+    if m_prov:
+        prov = m_prov.group(1).strip().lower()
+        if prov in {"qwen3cam", "soniox", "gemini", "openai", "grok", "vibevoice"}:
+            return prov
     if "CAM++" in head or TURN_TAG.match(raw.strip().splitlines()[-1] if raw.strip() else ""):
         return "qwen3cam"
     if re.search(r"^\[\d{1,2}:\d{2}\]\s*S\d+\s*[:：]", raw, re.M):
@@ -108,7 +114,7 @@ def parse(raw: str) -> tuple[list[Turn], dict]:
     """Split a transcript into turns plus header metadata."""
     meta: dict = {
         "voiceprint_session": "", "voiceprint_named": {}, "banners": [],
-        "intake": {},
+        "intake": {}, "asr_provider": "", "asr_model": "",
     }
     lines = raw.splitlines()
     body_lines = []
@@ -120,6 +126,11 @@ def parse(raw: str) -> tuple[list[Turn], dict]:
             except (TypeError, ValueError):
                 pass
             continue
+        m_prov = PROVIDER_HDR.match(ln)
+        if m_prov:
+            meta["asr_provider"] = m_prov.group(1) or ""
+            meta["asr_model"] = m_prov.group(2) or ""
+            continue
         if VOICEPRINT_HDR.match(ln):
             m = re.search(r"voiceprint_session:\s*(\S+)", ln)
             if m: