Split audio into proper_nouns_audio/, track JSON files in git

.gitignore

@@ -9,7 +9,10 @@ __pycache__/
 *.mp3
 *.flac
 output_audiobook/
-output_proper_nouns/
+proper_nouns_audio/
+
+# Generated data (JSON files in output_proper_nouns/ are tracked)
+output_proper_nouns/remaining_review.txt
 
 # Text files (except proper_nouns.txt)
 *.txt

generate_proper_noun_audio.py

@@ -24,8 +24,9 @@ from pathlib import Path
 from kokoro import KPipeline
 
 PROPER_NOUNS_FILE = Path("proper_nouns.txt")
-OUTPUT_DIR        = Path("output_proper_nouns")
-MANIFEST_FILE     = OUTPUT_DIR / "manifest.json"
+DATA_DIR          = Path("output_proper_nouns")   # JSON files — tracked in git
+AUDIO_DIR         = Path("proper_nouns_audio")     # WAV files — not tracked
+MANIFEST_FILE     = DATA_DIR / "manifest.json"
 VOICE             = "am_michael"
 SAMPLE_RATE       = 24000
 SPEED             = 1.0
@@ -96,7 +97,8 @@ def main() -> None:
     if device == "cuda":
         print(f"GPU:    {torch.cuda.get_device_name(0)}")
 
-    OUTPUT_DIR.mkdir(exist_ok=True)
+    DATA_DIR.mkdir(exist_ok=True)
+    AUDIO_DIR.mkdir(exist_ok=True)
 
     print(f"Parsing '{PROPER_NOUNS_FILE}' …")
     entries = parse_entries(PROPER_NOUNS_FILE)
@@ -118,7 +120,7 @@ def main() -> None:
     for i, (cat, entry) in enumerate(entries):
         slug = slugify(entry)
         wav_name = f"{slug}.wav"
-        wav_path = OUTPUT_DIR / wav_name
+        wav_path = AUDIO_DIR / wav_name
 
         if entry in manifest and wav_path.exists():
             skipped += 1

gui_proper_noun_player.py

@@ -55,11 +55,12 @@ os.environ.setdefault("HF_HUB_OFFLINE", "1")
 import sounddevice as sd
 import soundfile as sf
 
-MANIFEST_FILE        = Path("output_proper_nouns/manifest.json")
-OUTPUT_DIR           = Path("output_proper_nouns")
-REPLACEMENTS_DIR     = OUTPUT_DIR / "replacements_cache"
-CORRECT_FILE         = OUTPUT_DIR / "correct_words.json"
-FIXES_FILE           = OUTPUT_DIR / "pronunciation_fixes.json"
+DATA_DIR             = Path("output_proper_nouns")       # JSON files — tracked in git
+AUDIO_DIR            = Path("proper_nouns_audio")        # WAV files — not tracked
+MANIFEST_FILE        = DATA_DIR / "manifest.json"
+REPLACEMENTS_DIR     = AUDIO_DIR / "replacements_cache"
+CORRECT_FILE         = DATA_DIR / "correct_words.json"
+FIXES_FILE           = DATA_DIR / "pronunciation_fixes.json"
 SOURCE_TEXT          = Path("Audio Master Nem Full.txt")
 FIXED_TEXT_OUT       = Path("Audio Master Nem Full (TTS Fixed).txt")
 
@@ -417,7 +418,7 @@ class ProperNounAuditor(tk.Tk):
         wav_name = self.manifest.get(word)
         if not wav_name:
             return
-        wav_path = OUTPUT_DIR / wav_name
+        wav_path = AUDIO_DIR / wav_name
         if not wav_path.exists():
             messagebox.showwarning("Missing audio",
                                    f"No audio file for '{word}'.\n"
@@ -521,7 +522,7 @@ class ProperNounAuditor(tk.Tk):
             wav_name = self.manifest.get(word)
             if not wav_name:
                 return
-            wav_path = OUTPUT_DIR / wav_name
+            wav_path = AUDIO_DIR / wav_name
             if wav_path.exists():
                 wav_path.unlink()
             self.now_playing_var.set(f"… regen {word}")
@@ -687,7 +688,7 @@ class ProperNounAuditor(tk.Tk):
         if not words:
             messagebox.showinfo("Nothing to export", "No words left to review.")
             return
-        out = OUTPUT_DIR / "remaining_review.txt"
+        out = DATA_DIR / "remaining_review.txt"
         out.write_text("\n".join(words), encoding="utf-8")
         messagebox.showinfo("Exported",
                             f"{len(words)} words written to:\n{out}")
@@ -720,6 +721,7 @@ class ProperNounAuditor(tk.Tk):
 def main() -> None:
     if not MANIFEST_FILE.exists():
         print(f"Manifest not found: '{MANIFEST_FILE}'")
+        print("Run generate_proper_noun_audio.py first.")  # noqa
         print("Run generate_proper_noun_audio.py first.")
         raise SystemExit(1)
 

output_proper_nouns/pronunciation_fixes.json

@@ -0,0 +1,28 @@
+{
+  "Gadianton Robbers": "Gadeeantun Robbers",
+  "Gadianton": "Gadeeantun",
+  "Coriantumr": "Coryantomer",
+  "Laman": "Layman",
+  "Lehi And Nephi": "Leehi And Nephi",
+  "Lehi": "Leehi",
+  "Lehi Mathonihah": "Leehi Mathonihah",
+  "Lehis": "Leehis",
+  "Lehies": "Leehis",
+  "Liahona": "Leeahona",
+  "Moroni": "Morero-ni",
+  "Alma": "Al-ma",
+  "Gadiantons": "Gadeeantuns",
+  "Laban": "Layban",
+  "Mosiah": "Moziah",
+  "Mosiah The King": "Moziah The King",
+  "Nehors": "Kneehores",
+  "Samuel The Lamanite": "Samuel The Laymanite",
+  "Tarry": "Tarery",
+  "The Lamanite Twins": "The Laymanite Twins",
+  "The Lamanites Of Ammon": "The Laymanites Of Ammon",
+  "The Lamanites Of The Land Of Zarahemla": "The Laymanites Of The Land Of Zarahemla",
+  "The Lamanites Of The Land Southward": "The Laymanites Of The Land Southward",
+  "The Lamanites Of The People Of Ammon": "The Laymanites Of The People Of Ammon",
+  "The Lamb'S Book Of Life": "The Lamb's Book Of Life",
+  "The Land Of Nephi": "The Land Of Kneefi"
+}