docker: containerizzazione tts-server con GPU Vulkan (Dockerfile multi-stage + compose + entrypoint voci .spk/.rvq)

2026-08-13 20:06:55 +02:00
parent 3be42af9bb
commit 8b9361803e
6 changed files with 294 additions and 0 deletions
@@ -0,0 +1,72 @@
+#!/usr/bin/env python3
+"""Registra le voci clonate (.spk/.rvq) trovate in VOICE_DIR nel tts-server.
+
+Container-friendly: scansiona VOICE_DIR ricorsivamente; per ogni *.spk
+cerca il .rvq omonimo (obbligatorio) e il .txt omonimo (ref_text, opzionale;
+fallback: *_batch_ref.txt nella stessa directory).
+"""
+import base64
+import json
+import os
+import sys
+import urllib.request
+
+PORT = os.environ.get("TTS_PORT", "8881")
+URL = f"http://127.0.0.1:{PORT}/v1/audio/voices"
+VOICE_DIR = os.environ.get("VOICE_DIR", "/voices")
+
+
+def register(name, spk_path, rvq_path, ref_text):
+    spk_b64 = base64.b64encode(open(spk_path, "rb").read()).decode()
+    rvq_b64 = base64.b64encode(open(rvq_path, "rb").read()).decode()
+    body = {"name": name, "spk_b64": spk_b64, "rvq_b64": rvq_b64}
+    if ref_text:
+        body["ref_text"] = ref_text
+    req = urllib.request.Request(
+        URL, data=json.dumps(body).encode(),
+        headers={"Content-Type": "application/json"}, method="POST",
+    )
+    with urllib.request.urlopen(req, timeout=30) as r:
+        resp = json.loads(r.read().decode())
+        print(f"{name}: {r.status} {resp.get('status')}")
+        return True
+
+
+def main():
+    if not os.path.isdir(VOICE_DIR):
+        print(f"VOICE_DIR {VOICE_DIR} non esiste, salto registrazione")
+        return 0
+    ok = total = 0
+    for root, _dirs, files in os.walk(VOICE_DIR):
+        batch_ref = None
+        for f in files:
+            if f.endswith("_batch_ref.txt"):
+                batch_ref = open(os.path.join(root, f)).read()
+        for f in sorted(files):
+            if not f.endswith(".spk"):
+                continue
+            stem = f[: -len(".spk")]
+            name = stem.replace("_ref", "").replace("_vocals", "")
+            spk_path = os.path.join(root, f)
+            rvq_path = os.path.join(root, stem + ".rvq")
+            if not os.path.isfile(rvq_path):
+                print(f"{name}: rvq mancante ({rvq_path}), salto")
+                continue
+            txt_path = os.path.join(root, stem + ".txt")
+            ref_text = None
+            if os.path.isfile(txt_path):
+                ref_text = open(txt_path).read()
+            elif batch_ref:
+                ref_text = batch_ref
+            total += 1
+            try:
+                if register(name, spk_path, rvq_path, ref_text):
+                    ok += 1
+            except Exception as e:
+                print(f"{name}: ERRORE {e}")
+    print(f"\nRegistrate {ok}/{total} voci")
+    return 0 if ok == total else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())