feat: warn on empty transcripts and missing whisper backend in server.json tool

1 files changed, 35 insertions, 1 deletions

diff --git a/tools/make_audiocpp_server_json.py b/tools/make_audiocpp_server_json.py
index 40354eb..c999f49 100755
--- a/tools/make_audiocpp_server_json.py
+++ b/tools/make_audiocpp_server_json.py
@@ -38,7 +38,7 @@ from typing import Dict, Optional
 sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
 
 from converter import config
-from converter.tts import transcribe_reference_audio
+from converter.tts import transcribe_reference_audio, whisper_backend_available
 
 DEFAULT_HOST = "127.0.0.1"
 FALLBACK_PORT = 8080
@@ -307,6 +307,33 @@ def _print_next_steps(output_path: Path, include_custom: bool,
               "since speaker mode needs the CustomVoice model.")
 
 
+def print_empty_transcript_warning(voice_presets: Dict[str, dict]) -> None:
+    """Print a loud, final warning for voices whose transcript is empty.
+
+    A cloning preset with an empty ``reference_text`` will not produce a
+    usable voice (the server has nothing to match the reference audio
+    against for in-context cloning), so the user must edit server.json by
+    hand. This is printed last, after the next-steps, so it is the last
+    thing seen and hardest to miss.
+    """
+    empty = sorted(name for name, preset in voice_presets.items()
+                   if not preset.get("reference_text"))
+    if not empty:
+        return
+    bar = "=" * 70
+    print()
+    print(bar)
+    print("[WARNING] MANUAL TRANSCRIPTION REQUIRED")
+    print(bar)
+    listing = "  - " + "\n  - ".join(empty) if len(empty) > 1 else f"  - {empty[0]}"
+    print(f"The following voice preset(s) have an EMPTY reference_text in "
+          f"server.json:\n{listing}")
+    print("Those voices will NOT work until you add a manual transcription.")
+    print('Edit server.json and fill in the "reference_text" field for each '
+          "voice above with an accurate transcript of its reference .wav.")
+    print(bar)
+
+
 def main() -> int:
     parser = argparse.ArgumentParser(
         description="Generate a server.json for the audio.cpp audiocpp_server "
@@ -404,6 +431,12 @@ def main() -> int:
     if wav_dir is not None:
         wav_files = find_wav_files(wav_dir)
         if wav_files:
+            if whisper_backend_available() is None:
+                print("[WARNING] Neither faster_whisper nor whisper was found, so "
+                      "reference .wav files cannot be transcribed automatically and "
+                      "every reference_text will be empty.")
+                print('          Did you remember to "conda activate qwen3-tts"? '
+                      "Transcripts must be added by hand (see the warning at the end).")
             voice_presets = build_voice_presets(wav_files, args.whisper_model)
         else:
             print(f"[WARNING] No .wav files found in {wav_dir}; writing the "
@@ -436,6 +469,7 @@ def main() -> int:
     print(f"\n[OK] Wrote {args.output} with {len(server_config['models'])} "
           f"model(s) and {len(voice_presets)} voice preset(s)")
     _print_next_steps(args.output, include_custom, include_clone, voice_presets)
+    print_empty_transcript_warning(voice_presets)
     return 0