fixed book markers

create_audiobook_nem.py

@@ -4,12 +4,17 @@ audiobook_nem.py
 Generate the Book of the Nem audiobook — one unique voice per book/section.
 
 Usage:
-    python audiobook_nem.py
+    python create_audiobook_nem.py                   # all enabled books
+    python create_audiobook_nem.py --list            # list available book labels
+    python create_audiobook_nem.py Introduction
+    python create_audiobook_nem.py "Book of Hagoth"
+    python create_audiobook_nem.py Introduction "Book of Hagoth"
 
-To skip a section, comment out its entry in BOOKS below.
+To permanently skip a section, comment out its entry in BOOKS below.
 Output .wav files are written to OUTPUT_DIR (created automatically).
 """
 
+import argparse
 import re
 import time
 import numpy as np
@@ -41,30 +46,30 @@ LANG_CODE     = "a"   # 'a' = American English
 #   am_santa   – American male               [downloaded] (not used)
 
 # ── Book definitions ───────────────────────────────────────────────────────────
-# Format: (label, start_marker, voice, output_wav)
-#   start_marker – exact text of the FIRST line of the section header in the source
-#                  (leading/trailing whitespace is ignored when matching)
+# Format: (label, (start_line1, start_line2), voice, output_wav)
+#   start_line1 – exact text of the FIRST line of the section header
+#   start_line2 – prefix of the SECOND line (used together for unambiguous matching)
 #   voice        – Kokoro voice name
 #   output_wav   – filename saved inside OUTPUT_DIR
 #
 # Comment out any line to skip that section entirely.
 BOOKS = [
-    # label                       start_marker                       voice         output_wav
-    ("Introduction",              "Introduction",                    "af_heart",   "00_introduction.wav"),
-    ("Book of Hagoth",            "THE BOOK OF HAGOTH",              "am_fenrir",  "01_hagoth.wav"),
-    # ("Shi-Tugo I",                "THE FIRST BOOK OF SHI-TUGO",      "am_eric",    "02_shi_tugo_1.wav"),
-    # ("Sanempet",                  "THE BOOK OF SANEMPET",            "am_liam",    "03_sanempet.wav"),
-    # ("Oug",                       "THE BOOK OF OUG",                 "am_michael", "04_oug.wav"),
-    # ("Temple Writings of Oug",    "THE BOOK OF",                     "am_michael", "05_temple_writings_oug.wav"),
-    # ("Sacred Temple Writings",    "THE SACRED",                      "am_michael", "06_sacred_temple_writings.wav"),
-    # ("Samuel the Lamanite I",     "THE FIRST BOOK",                  "am_echo",    "07_samuel_lamanite_1.wav"),
-    # ("Samuel the Lamanite II",    "THE SECOND BOOK",                 "am_echo",    "08_samuel_lamanite_2.wav"),
-    # ("Manti",                     "THE BOOK OF MANTI",               "am_onyx",    "09_manti.wav"),
-    # ("Pa Nat I",                  "THE FIRST BOOK OF PA NAT",        "af_nicole",  "10_pa_nat_1.wav"),
-    # ("Moroni I",                  "THE FIRST BOOK OF MORONI",        "am_adam",    "11_moroni_1.wav"),
-    # ("Moroni II",                 "THE SECOND BOOK OF MORONI",       "am_adam",    "12_moroni_2.wav"),
-    # ("Moroni III",                "THE THIRD BOOK OF MORONI",        "am_adam",    "13_moroni_3.wav"),
-    # ("Shioni",                    "THE BOOK OF SHIONI",              "am_puck",    "14_shioni.wav"),
+    # label                       (start_line1,                    start_line2)                           voice         output_wav
+    ("Introduction",              ("Introduction",                 "The Book of the Nem"),                "af_heart",   "00_introduction.wav"),
+    ("Book of Hagoth",            ("THE BOOK OF HAGOTH",           "THE SON OF HAGMENI,"),                 "am_fenrir",  "01_hagoth.wav"),
+    ("Shi-Tugo I",                ("THE FIRST BOOK OF SHI-TUGO",  "FORMER WARRIOR, AMMONITE"),            "am_eric",    "02_shi_tugo_1.wav"),
+    ("Sanempet",                  ("THE BOOK OF SANEMPET",        "THE SON OF HAGMENI,"),                 "am_liam",    "03_sanempet.wav"),
+    ("Oug",                       ("THE BOOK OF OUG",             "THE SON OF SANEMPET"),                 "am_michael", "04_oug.wav"),
+    ("Temple Writings of Oug",    ("THE BOOK OF",                 "THE TEMPLE WRITINGS"),                "am_michael", "05_temple_writings_oug.wav"),
+    ("Sacred Temple Writings",    ("THE SACRED",                  "TEMPLE WRITINGS"),                     "am_michael", "06_sacred_temple_writings.wav"),
+    ("Samuel the Lamanite I",     ("THE FIRST BOOK",              "OF SAMUEL THE LAMANITE"),             "am_echo",    "07_samuel_lamanite_1.wav"),
+    ("Samuel the Lamanite II",    ("THE SECOND BOOK",             "OF SAMUEL THE LAMANITE"),             "am_echo",    "08_samuel_lamanite_2.wav"),
+    ("Manti",                     ("THE BOOK OF MANTI",           "THE SON OF OUG"),                      "am_onyx",    "09_manti.wav"),
+    ("Pa Nat I",                  ("THE FIRST BOOK OF PA NAT",    "THE DAUGHTER OF SHIMLEI"),             "af_nicole",  "10_pa_nat_1.wav"),
+    ("Moroni I",                  ("THE FIRST BOOK OF MORONI",    "THE SON OF MORMON,"),                  "am_adam",    "11_moroni_1.wav"),
+    ("Moroni II",                 ("THE SECOND BOOK OF MORONI",   "THE SON OF MORMON,"),                  "am_adam",    "12_moroni_2.wav"),
+    ("Moroni III",                ("THE THIRD BOOK OF MORONI",    "THE SON OF MORMON,"),                  "am_adam",    "13_moroni_3.wav"),
+    ("Shioni",                    ("THE BOOK OF SHIONI",          "THE SON OF MORONI"),                   "am_puck",    "14_shioni.wav"),
 ]
 
 # ── Helpers ────────────────────────────────────────────────────────────────────
@@ -72,23 +77,24 @@ BOOKS = [
 def load_and_split(source: Path, books: list) -> dict[str, str]:
     """
     Read the source file and split it into sections keyed by label.
-    Each section starts at its start_marker line and ends just before the
-    next section's start_marker.
+    Each section starts at its (start_line1, start_line2) marker pair and
+    ends just before the next section's marker.
     """
     raw_lines = source.read_text(encoding="utf-8").splitlines()
 
-    # Build a mapping: marker_text → index in BOOKS
-    markers = [(label, marker.strip()) for label, marker, _, _ in books]
+    # Build a mapping: (label, line1, line2) for each book
+    markers = [(label, m[0].strip(), m[1].strip()) for label, m, _, _ in books]
 
-    # Find the line index of each marker's first occurrence
+    # Find the line index of each marker's first occurrence (two-line match)
     marker_positions: list[tuple[int, int]] = []   # (line_idx, books_idx)
-    for book_idx, (label, marker) in enumerate(markers):
-        for line_idx, line in enumerate(raw_lines):
-            if line.strip() == marker:
+    for book_idx, (label, m1, m2) in enumerate(markers):
+        for line_idx, line in enumerate(raw_lines[:-1]):
+            if (line.strip() == m1 and
+                    raw_lines[line_idx + 1].strip().startswith(m2)):
                 marker_positions.append((line_idx, book_idx))
                 break
         else:
-            print(f"  ⚠  Marker not found for '{label}': '{marker}' — skipping")
+            print(f"  ⚠  Marker not found for '{label}': '{m1}' / '{m2}' — skipping")
 
     marker_positions.sort(key=lambda x: x[0])
 
@@ -154,6 +160,38 @@ def generate_audio(pipeline: KPipeline, text: str, voice: str,
 # ── Main ───────────────────────────────────────────────────────────────────────
 
 def main() -> None:
+    # ── CLI ────────────────────────────────────────────────────────────
+    parser = argparse.ArgumentParser(description="Generate Nem audiobook sections.")
+    parser.add_argument(
+        "books", nargs="*",
+        help="Labels of sections to generate (default: all enabled books). "
+             "Use --list to see available labels."
+    )
+    parser.add_argument(
+        "--list", action="store_true",
+        help="Print all enabled book labels and exit."
+    )
+    args = parser.parse_args()
+
+    enabled_labels = [label for label, _, _, _ in BOOKS]
+
+    if args.list:
+        print("Enabled books:")
+        for label in enabled_labels:
+            print(f"  {label}")
+        return
+
+    # Filter to requested subset, preserving BOOKS order
+    if args.books:
+        unknown = [b for b in args.books if b not in enabled_labels]
+        if unknown:
+            print(f"Unknown book label(s): {', '.join(unknown)}")
+            print(f"Run with --list to see available labels.")
+            return
+        run_books = [b for b in BOOKS if b[0] in args.books]
+    else:
+        run_books = list(BOOKS)
+
     device = "cuda" if torch.cuda.is_available() else "cpu"
     print(f"Device: {device}")
     if device == "cuda":
@@ -164,8 +202,10 @@ def main() -> None:
     print(f"\nSource: '{SOURCE_FILE}'"
           + (" ✓ (TTS fixed)" if SOURCE_FILE == _FIXED_FILE else
              " ⚠ (original — run 'Apply Fixes to Text' in the GUI to use phonetic fixes)"))
+    # Always split using ALL books for correct section boundaries,
+    # but only generate for run_books.
     sections = load_and_split(SOURCE_FILE, BOOKS)
-    print(f"  Found {len(sections)} sections.\n")
+    print(f"  Found {len(sections)} sections ({len(run_books)} selected).\n")
 
     print("Initialising Kokoro pipeline …")
     pipeline = KPipeline(lang_code=LANG_CODE)
@@ -173,14 +213,26 @@ def main() -> None:
     # Pre-compute char counts for all sections so we can estimate ETAs
     section_chars: dict[str, int] = {
         label: len(clean_text(sections[label]))
-        for label, _, _, _ in BOOKS
+        for label, _, _, _ in run_books
         if label in sections
     }
 
+    # Print char count summary before starting
+    print(f"\n{'─' * 52}")
+    print(f"  {'Section':<30}  {'Chars':>8}")
+    print(f"{'─' * 52}")
+    for label, _, _, wav_name in run_books:
+        if label in section_chars:
+            print(f"  {label:<30}  {section_chars[label]:>8,}")
+    print(f"{'─' * 52}")
+    total_chars = sum(section_chars.values())
+    print(f"  {'TOTAL':<30}  {total_chars:>8,}")
+    print()
+
     chars_per_sec: float | None = None   # derived from the first book that finishes
     timing_rows: list[tuple[str, int, float]] = []  # (label, chars, elapsed)
 
-    for label, marker, voice, wav_name in BOOKS:
+    for label, _marker, voice, wav_name in run_books:
         if label not in sections:
             continue
 

gui_proper_noun_player.py

@@ -84,8 +84,11 @@ MAUVE   = "#cba6f7"
 def play_async(path: Path) -> None:
     sd.stop()
     def _play():
-        data, sr = sf.read(str(path), dtype="float32")
-        sd.play(data, sr)
+        try:
+            data, sr = sf.read(str(path), dtype="float32")
+            sd.play(data, sr)
+        except Exception as exc:
+            print(f"[audio] playback error: {exc}")
     threading.Thread(target=_play, daemon=True).start()
 
 
@@ -119,11 +122,14 @@ def synth_and_play(text: str, on_ready=None) -> None:
     *on_ready(path)* is called on the same thread once the file is written.
     """
     def _run():
-        path = _synth_to_cache(text)
-        if path:
-            if on_ready:
-                on_ready(path)
-            play_async(path)
+        try:
+            path = _synth_to_cache(text)
+            if path:
+                if on_ready:
+                    on_ready(path)
+                play_async(path)
+        except Exception as exc:
+            print(f"[synth] error synthesising '{text}': {exc}")
 
     threading.Thread(target=_run, daemon=True).start()
 
@@ -216,6 +222,8 @@ class ProperNounAuditor(tk.Tk):
 
         self._build_ui()
         self._refresh_all()
+        self._alive = True
+        self.protocol("WM_DELETE_WINDOW", self._on_close)
 
         # Window-level hotkeys (work even when a listbox has keyboard focus)
         self.bind("<space>",  lambda e: self._replay())
@@ -224,6 +232,19 @@ class ProperNounAuditor(tk.Tk):
                   if self.focus_get() is not self._fix_entry else None)
         self.bind("<Escape>", lambda e: self._reset_fix_entry())
 
+    def _on_close(self) -> None:
+        self._alive = False
+        sd.stop()
+        self.destroy()
+
+    def _safe_after(self, ms: int, func) -> None:
+        """Schedule func on the Tk thread; silently no-ops if window is gone."""
+        if self._alive:
+            try:
+                self.after(ms, func)
+            except RuntimeError:
+                pass
+
     # ── UI construction ────────────────────────────────────────────────────────
 
     def _build_ui(self) -> None:
@@ -457,7 +478,7 @@ class ProperNounAuditor(tk.Tk):
             self.fix_var.set(replacement)
             self.now_playing_var.set(f"… {replacement}")
             def _on_ready(_path):
-                self.after(0, lambda: self.now_playing_var.set(replacement))
+                self._safe_after(0, lambda: self.now_playing_var.set(replacement))
             synth_and_play(replacement, on_ready=_on_ready)
         else:
             # Correct list — show word in fix entry, play it
@@ -515,7 +536,7 @@ class ProperNounAuditor(tk.Tk):
                 target.unlink()
             self.now_playing_var.set(f"… regen {fix_text}")
             def _on_ready(_p):
-                self.after(0, lambda: self.now_playing_var.set(fix_text))
+                self._safe_after(0, lambda: self.now_playing_var.set(fix_text))
             synth_and_play(fix_text, on_ready=_on_ready)
         else:
             # Re-gen the manifest audio for the review word
@@ -528,18 +549,21 @@ class ProperNounAuditor(tk.Tk):
             self.now_playing_var.set(f"… regen {word}")
 
             def _regen():
-                import warnings, numpy as np
-                pipeline = _get_pipeline()
-                chunks = []
-                with warnings.catch_warnings():
-                    warnings.filterwarnings("ignore", category=UserWarning)
-                    for _, _, audio in pipeline(word, voice=VOICE):
-                        if audio is not None:
-                            chunks.append(audio)
-                if chunks:
-                    sf.write(str(wav_path), np.concatenate(chunks), SAMPLE_RATE)
-                    self.after(0, lambda: self.now_playing_var.set(word))
-                    play_async(wav_path)
+                try:
+                    import warnings, numpy as np
+                    pipeline = _get_pipeline()
+                    chunks = []
+                    with warnings.catch_warnings():
+                        warnings.filterwarnings("ignore", category=UserWarning)
+                        for _, _, audio in pipeline(word, voice=VOICE):
+                            if audio is not None:
+                                chunks.append(audio)
+                    if chunks:
+                        sf.write(str(wav_path), np.concatenate(chunks), SAMPLE_RATE)
+                        self._safe_after(0, lambda: self.now_playing_var.set(word))
+                        play_async(wav_path)
+                except Exception as exc:
+                    print(f"[regen] error for '{word}': {exc}")
 
             threading.Thread(target=_regen, daemon=True).start()
 
@@ -669,17 +693,21 @@ class ProperNounAuditor(tk.Tk):
         self._pregen_status_var.set(f"0 / {new_count} new  ({already} cached)")
 
         def _run():
-            done = 0
-            for rep in replacements:
-                cache_path = REPLACEMENTS_DIR / f"{_slug(rep)}.wav"
-                if not cache_path.exists():
-                    _synth_to_cache(rep)
-                    done += 1
-                    self.after(0, lambda d=done, t=new_count:
-                               self._pregen_status_var.set(f"{d} / {t} synthesised…"))
-            self.after(0, lambda: self._pregen_status_var.set(
-                f"Done — {total} clips ready"))
-            self.after(0, lambda: self._pregen_btn.config(state="normal"))
+            try:
+                done = 0
+                for rep in replacements:
+                    cache_path = REPLACEMENTS_DIR / f"{_slug(rep)}.wav"
+                    if not cache_path.exists():
+                        _synth_to_cache(rep)
+                        done += 1
+                        self._safe_after(0, lambda d=done, t=new_count:
+                                   self._pregen_status_var.set(f"{d} / {t} synthesised…"))
+                self._safe_after(0, lambda: self._pregen_status_var.set(
+                    f"Done — {total} clips ready"))
+            except Exception as exc:
+                print(f"[pregen] error: {exc}")
+            finally:
+                self._safe_after(0, lambda: self._pregen_btn.config(state="normal"))
 
         threading.Thread(target=_run, daemon=True).start()
 

output_proper_nouns/correct_words.json

@@ -1,15 +1,13 @@
 [
+  "Ninety-Two",
+  "Gilgal",
   "Nat",
   "Monoriah",
   "Akim",
   "Amoron",
-  "Migdan Idi",
   "Migdan",
   "Midgan-Idi",
-  "Midgan Idi",
   "Midgan",
-  "Mic",
-  "Mi",
   "Mentina",
   "Hemeacum",
   "Micah",
@@ -21,7 +19,6 @@
   "Kishkumen",
   "Kee",
   "Kayith",
-  "Kay",
   "Pah",
   "Kamiakim",
   "Corian-Co-Hah",
@@ -29,9 +26,6 @@
   "Chunish",
   "Chu",
   "Cheem",
-  "Co",
-  "Thanksgiving",
-  "Way",
   "Zoreth",
   "Zoramites",
   "Zoramite",
@@ -42,374 +36,120 @@
   "Zen",
   "Zeezret",
   "Zedekiah",
-  "King",
   "Zarahemla",
-  "Yourselves",
-  "Yourself",
-  "Yours",
-  "Kingdom",
-  "Day",
-  "Young",
   "Yohks",
-  "Yesterday",
-  "Yay",
-  "Writings",
-  "Write",
-  "Worthy",
-  "Worlds",
-  "World",
   "Worketh",
-  "Word",
-  "Women",
-  "Woman",
   "Woe",
-  "Wives",
-  "Winter",
   "Winebag",
   "Winding",
-  "Wind",
   "Willow",
-  "Wife",
-  "Whom",
   "Whereupon",
   "Wherefore",
-  "Whatsoever",
-  "Western",
-  "West",
-  "Weeks",
-  "Wee",
-  "Ways",
   "Waylit",
   "Wayat",
-  "Waters",
-  "Water",
-  "Washing",
   "Wards",
-  "War",
   "Wallohitwah",
-  "Walk",
   "Wah",
-  "Voice",
-  "Virtue",
   "Vineyards",
   "Vineyard",
   "Verily",
   "Veil",
-  "Heaven",
-  "Valley",
   "Urim",
   "Unquenchable",
-  "Fire",
-  "Universe",
-  "Universal",
-  "United",
   "Two-Fold",
-  "Two",
-  "Thousand",
-  "Months",
-  "Hundred",
-  "Days",
-  "Twins",
-  "Twenty",
-  "Five",
-  "Years",
-  "Twelve",
   "Tugo",
-  "Truth",
-  "True",
-  "Tree",
-  "Traveling",
-  "Councils",
   "Peli",
   "Tornit",
   "Torieth",
   "Tor",
-  "Toniah Lotnah",
   "Toniah",
-  "Tomorrow",
-  "Token",
-  "Today",
   "Tithe",
   "Timothy",
-  "Son",
   "Brethren",
-  "Thunder",
   "Thummim",
-  "Three",
-  "Quarters",
-  "Thousands",
-  "Miles",
   "Knewest",
   "Perilous",
-  "Year",
-  "Present",
-  "Land",
   "Northward",
-  "Holy",
-  "Spirit",
-  "Place",
-  "Ghost",
-  "Great",
-  "Council",
   "Everlasting",
   "Covenant",
-  "Thirteen",
-  "Third",
-  "Last",
-  "Men",
-  "Spirits",
   "Firstborn",
-  "River",
-  "Sea",
-  "Mountains",
   "Anointing",
   "Wasatch",
-  "Front",
-  "Warm",
-  "Mob",
-  "Law",
-  "Restoration",
-  "Order",
-  "Sons",
-  "Daughters",
   "Elohim",
   "Heavenly",
-  "People",
-  "Life",
-  "Knowledge",
-  "Good",
-  "Evil",
-  "Thirty",
-  "Eighth",
-  "Book",
-  "Lodge",
-  "Terrible",
   "Terrestrial",
-  "Temple",
-  "Lord",
   "Eve",
   "Bountiful",
-  "Hill",
   "Tamahu-Ah",
-  "Sweat",
-  "Sure",
-  "Sign",
-  "Nail",
-  "Summer",
-  "Spring",
   "Levi",
-  "Father",
-  "Snake",
-  "Sixty",
-  "Ninth",
-  "Sixth",
   "Shortest",
-  "Seventy",
-  "Fifth",
-  "Seventh",
-  "Sacred",
-  "Direction",
-  "Sees",
   "Habitation",
-  "Seeks",
-  "Second",
   "Endowment",
-  "Season",
-  "Coast",
   "Salten",
-  "Record",
-  "Pipe",
   "Herbs",
   "Hearth",
   "Garments",
-  "Directions",
-  "Animals",
   "Sabbath",
   "Robe",
   "Priesthood",
   "Akish",
-  "Right",
-  "Prayer",
   "Remnant",
-  "House",
   "Israel",
   "Jacob",
   "Purification",
   "Ammonites",
   "Melchizedek",
-  "Power",
-  "Mother",
-  "God",
-  "Sacrifice",
   "Adam",
-  "Ceremony",
-  "Gulf",
   "Hagoth",
   "Corianton",
   "Ammon",
   "Patriarchal",
-  "Grip",
-  "Path",
-  "Creator",
-  "Past",
-  "Ten",
-  "Orders",
-  "North",
-  "Country",
   "Ninety",
-  "Night",
-  "Next",
-  "Newborn",
-  "Children",
-  "New",
   "Nemenha",
   "Nem",
-  "Volume",
-  "Another",
-  "Testament",
-  "Jesus",
-  "Christ",
-  "Prophet",
-  "Living",
-  "Morning",
-  "Middle",
-  "Archives",
-  "Medicine",
-  "Dance",
-  "Man",
-  "Higher",
   "Lord'S",
-  "Harvest",
-  "Looks",
-  "Light",
   "Levitical",
-  "Laying",
-  "Hands",
-  "Laws",
-  "Gospel",
-  "Revelation",
   "Obedience",
   "Consecration",
   "Chastity",
   "Latter-Day",
-  "Latter",
-  "Lands",
   "Southward",
-  "Jerusalem",
   "Desolation",
-  "Lake",
-  "Islands",
-  "Hour",
-  "Hosts",
-  "Host",
-  "City",
-  "High",
-  "Priest",
-  "Region",
-  "Guide",
-  "Star",
-  "Growing",
-  "Salt",
   "Healer",
-  "Peace",
-  "Gift",
-  "Healing",
-  "General",
   "Nespelem",
-  "Friends",
-  "Fourth",
-  "Four",
   "Forty-Two",
   "Fortieth",
-  "Following",
   "Sixty-Seventh",
-  "First",
-  "Home",
-  "Pa",
   "Firmament",
-  "Final",
-  "Festival",
-  "Lights",
-  "Fair",
-  "Ones",
-  "End",
-  "Elect",
   "Eighty",
-  "Eastern",
-  "East",
-  "Earth",
   "Dreadful",
   "Coriantumr",
   "Savior",
   "Mayan",
   "Elders",
-  "Mothers",
-  "Community",
-  "Church",
-  "Certain",
-  "Common",
-  "Consent",
-  "Cold",
-  "Josh",
   "Gad",
   "Enoch",
-  "Saints",
-  "Chiefs",
-  "Indians",
   "Celestial",
-  "Glory",
   "Canyons",
-  "Buffalo",
-  "Breath",
-  "Brass",
-  "Plates",
-  "Bowl",
   "Incense",
   "Mormon",
   "Ether",
-  "Ancient",
-  "Quarter",
-  "Tenth",
-  "Tens",
   "Tempter",
   "Temnet",
   "Telleth",
   "Teemkt",
-  "Tee",
   "Tay",
   "Tarramarhah",
-  "Tan",
   "Tamahu",
-  "Talking",
-  "Talk",
   "Tah",
   "Sweetgrass",
   "Supposeth",
   "Supper",
-  "Superior",
-  "Sun",
   "Sufficeth",
   "Subdue",
   "Lucifer",
-  "Stones",
   "Stephat",
-  "Stars",
-  "Stakes",
-  "Spiritual",
-  "Spine",
   "Speaketh",
-  "Speaker",
-  "Sovereign",
-  "South",
-  "Time",
-  "Ago",
-  "Later",
-  "Date",
-  "Future",
-  "Sky",
-  "Sixteen",
-  "Age",
-  "Six",
   "Sineth",
   "Simeon",
   "Sidon",
@@ -429,81 +169,50 @@
   "Shadowing",
   "Sha",
   "Sevim",
-  "Several",
-  "Hours",
-  "Seventeen",
-  "Seven",
   "Setteth",
-  "Set",
-  "Session",
-  "Servant",
   "Seer",
   "Seeketh",
-  "Seek",
-  "Seat",
   "Sealing",
   "Saviors",
   "Satan",
   "Sanith",
   "Saneth",
-  "San",
-  "Stretch",
   "Spake",
   "Preach",
-  "Answered",
   "Samuel",
   "Samith",
   "Samal",
   "Salamander",
-  "Safety",
-  "Plants",
-  "Manner",
   "Sacrament",
   "Sabel-Nah",
   "Sabel",
   "Sabbaths",
-  "Room",
   "Robbers",
   "Rhen",
   "Resurrected",
-  "Resume",
   "Repent",
-  "Remove",
   "Rejoice",
   "Redeemer",
-  "Recall",
-  "Queens",
   "Prophets",
   "Moroni",
   "Prophecy",
-  "Promise",
-  "Priests",
   "Priestesses",
   "Priestess",
-  "President",
   "Preacher",
   "Prayeth",
-  "Pray",
   "Potal",
   "Porinor",
   "Por",
-  "Plan",
-  "Plains",
-  "Places",
   "Pingwit",
   "Pharaoh",
   "Peter",
   "James",
   "John",
-  "Person",
   "Perisheth",
-  "Altar",
   "Penith",
   "Pel",
-  "Pee",
   "Peacemaker",
   "Parim",
-  "Parents",
   "Parah",
   "Panith-Het",
   "Panith",
@@ -517,101 +226,50 @@
   "Hem",
   "Pagwit",
   "Pac-Sineth",
-  "Pac",
   "Ordinance",
-  "One",
-  "Forty",
-  "Half",
-  "Omega",
-  "Old",
   "Ohmer",
-  "Oh",
-  "Observe",
   "Nu",
   "Notwithstanding",
   "Nomiah-Min",
   "Nomiah",
-  "Min",
   "Noahs",
   "Noah",
-  "Ninety-Two Years",
-  "Nine",
   "Nin-Shepa",
   "Nin",
-  "Week",
-  "Name",
-  "Hills",
   "Nespelite",
-  "Nay",
   "Nathah",
   "Nemenhah",
   "Nemen",
-  "Neighbor",
-  "Nature",
-  "Natural",
-  "Narrator",
-  "Myself",
-  "Chosen",
   "Mulekites",
   "Mulekite",
   "Mulek",
   "Muel",
   "Moveth",
-  "Mouth",
-  "Mouse",
-  "Mountain",
-  "Mount",
-  "Fathers",
   "Moses",
   "Morrow",
   "Morin",
   "Moriantum",
-  "Moon",
-  "Millions",
   "Michael",
   "Methuselah",
   "Messengers",
   "Melek",
-  "Meet",
-  "Fall",
-  "Master",
   "Manna",
-  "Maker",
-  "Love",
-  "Lords",
-  "Look",
-  "Lone",
   "Lodges",
-  "Lo",
-  "Lives",
   "Limhi",
-  "Lightning",
   "Levites",
   "Levite",
-  "Lay",
-  "Lamb",
-  "Lakes",
   "Korim",
   "Knoweth",
-  "Know",
   "Kinsman",
-  "Kings",
   "Mosiah",
-  "Keen",
-  "Judgment",
   "Judgeth",
-  "Judge",
   "Judah",
   "Joseph",
   "Joram",
   "Revelator",
-  "Beloved",
-  "Jews",
-  "Himself",
   "Jehovah",
   "Jaredites",
   "Jaredite",
-  "Jared",
   "Jaguar",
   "Jacobite",
   "Israelite",
@@ -621,50 +279,26 @@
   "Isaiah",
   "Isabel",
   "Isaac",
-  "Instructor",
-  "Instruction",
-  "Inner",
-  "Indigenous",
-  "Americans",
   "Husbands",
-  "Husband",
   "Hundredth",
-  "Hundreds",
-  "Hudson",
-  "Bay",
   "Howbeit",
   "Hosanna",
   "Hopeth",
-  "Child",
   "Holiness",
-  "Hold",
   "Hin",
   "Himneth",
   "Hez",
   "Heth",
   "Het",
-  "Heroes",
-  "Hero",
   "Heirs",
-  "Hebrew",
   "Heavens",
-  "Beings",
-  "Heart",
   "Hearken",
   "Healers",
-  "Head",
-  "Hay",
   "Harlot",
   "Ham",
   "Hemen",
-  "Guides",
-  "Guardian",
   "Groweth",
-  "Grandmother",
   "Grandfathers",
-  "Grandfather",
-  "Governor",
-  "Gods",
   "Godliness",
   "Godhead",
   "Gideon",
@@ -672,51 +306,28 @@
   "Gentile",
   "Gee",
   "Gaudy",
-  "Gate",
-  "Garden",
-  "Fourteen",
   "Forty-Nine",
   "Forgetfulness",
-  "Minutes",
-  "Fifty",
   "Finisher",
   "Findeth",
-  "Figure",
   "Feather",
-  "Farewell",
   "Falleth",
-  "Faith",
   "Exalted",
-  "Being",
   "Exaltation",
-  "Evening",
-  "Eternal",
   "Ephraim",
   "Envieth",
-  "English",
-  "Else",
-  "Eleven",
-  "Election",
-  "Eight",
   "Egyptus",
-  "Egyptian",
   "Egypt",
   "Eden",
-  "Earlier",
-  "Eagle",
   "Dogwood",
   "Doeth",
   "Disciples",
   "Disciple",
   "Discernment",
-  "Devil",
   "Desolate",
   "Desireth",
   "Depart",
-  "Deep",
-  "Deaths",
   "Days'",
-  "Short",
   "Aaron",
   "Abel",
   "Abraham",
@@ -724,65 +335,28 @@
   "Adamant",
   "Adversary",
   "Afar",
-  "Afternoon",
-  "Alpha",
-  "America",
   "Amulek",
-  "Appointed",
-  "Angel",
-  "Angels",
   "Anith",
   "Anointed",
-  "Anti",
   "Apostle",
-  "Arise",
-  "Arm",
-  "Little",
-  "Least",
   "Atonement",
   "Availeth",
   "Babylon",
   "Baptism",
-  "Baptist",
-  "Begin",
   "Begotten",
   "Belay",
   "Believeth",
-  "Bend",
   "Benjamites",
-  "Big",
-  "Blessed",
-  "Blessing",
-  "Body",
-  "Break",
   "Brigham",
   "Bringeth",
   "Meekness",
-  "Brother",
-  "Bush",
   "Cain",
-  "Calling",
-  "Captain",
   "Cedar",
-  "Celebration",
-  "Celebrations",
-  "Chapters",
-  "Chief",
-  "Churches",
-  "Cities",
   "Laman",
   "Claimeth",
-  "Clan",
   "Coasts",
-  "Come",
   "Comforter",
   "Condemn",
   "Corian",
-  "Cosmos",
-  "Counsel",
-  "County",
-  "Creation",
-  "Cried",
-  "Daily",
-  "Dead"
+  "Cosmos"
 ]

output_proper_nouns/pronunciation_fixes.json

@@ -1,11 +1,8 @@
 {
-  "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",
@@ -14,15 +11,14 @@
   "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"
+  "Nephihah": "Kneefihah",
+  "Nephihet": "Kneefihet",
+  "Nephite": "Kneefite",
+  "Nephites": "Kneefites",
+  "Nephi-Im": "Kneefi-Im",
+  "Nephitish": "Kneefitish",
+  "Zenephi": "Zekneefi",
+  "Nephi": "Kneefi"
 }