Everything in one commit

.gitignore

@@ -0,0 +1 @@
+.idea/

README.md

@@ -0,0 +1,49 @@
+Ancient Greek Reader NLP
+========================
+
+__A lack of audio content is a major hurdle to learning Ancient Greek__. So I decided to tackle this problem with NLP.
+
+How Does It Work
+----------------
+
+OpenAI will read Ancient Greek text with a modern Greek pronunciation. What's different about OpenAI from other
+Text-to-Speech tools is that OpenAI is unaffected by the different accents and breathing marks in Ancient Greek. It will
+simply read the Ancient Greek text in modern pronunciation with the accents in the right places. Studying Ancient Greeek
+with modern pronunciation is simply not satisfactory for me, though, so I started messing around with the text to see if
+I could get the pronunciation closer to Erasmian/Attic/whatever we want to call it. We can simply replace letters in the
+Greek words with Latin letters to try and get what we want.
+
+Here is an example sentence.
+
+This is the original text, which OpenAI will read in Modern Greek with no problem:
+
+> Σόλων ἦν συνετώτατος πάντων τῶν Ἀθηναίων, τὴν γὰρ σοφίαν αὐτοῦ οὐ μόνον οἱ πολῖται ἐθαύμαζον, ἀλλὰ καὶ οἱ ἂλλοι
+>  Ἓλληνες πάντες, πολλοὶ δὲ καὶ τῶν βαρβάρων.
+
+And here is the same but with letters replaced to try and get OpenAI to read in an "Attic" pronunciation:
+
+> sόλωn en sunetώtαtος πάntωn tón aθenáiωn, tén γáρ sοφίan autu u μόnon hoi πολítαi eθáuμαζon, aλλá kái hoi áλλοi
+> Héλλeneς πάnteς, πολλói δé kái tón βαρβάρωn.
+
+A huge list of [letter replacements](./ancient-greek-phonemes.txt) has been made to try and imitate Attic pronunciation
+as closely as possible. The result is pretty solid and is close enough to be useful for creating audio files for texts
+where we don't have any audio recordings.
+[Checkout this "Attic" pronounciation example](https://qubitpi.github.io/ancient-greek-reader/)
+
+How to Use It (WIP)
+-------------------
+
+Here is a __WIP__ instruction: 
+
+1. Get an accurate Ancient Greek text and save it to a file named __original.txt__.
+   [Perseus Digital Library](https://www.perseus.tufts.edu/hopper/) is a great source.
+2. Run replacement:
+
+   - `python3 convert.py`
+
+3. Convert txt to epub. [Calibre](https://calibre-ebook.com/) works pretty well for this.
+4. Use https://github.com/p0n1/epub_to_audiobook to generate audio
+
+> [!CAUTION]
+>
+> OpenAI [billing](https://platform.openai.com/settings/organization/billing/overview) will apply to the last step

ancient-greek-phonemes.txt

@@ -0,0 +1,274 @@
+κ->k
+ε->e
+ι->i
+οῖ->ói
+τ->t
+σ->s
+Τ->t
+Σ->s
+οὕ->hú
+οῦ->u
+αύ->áu
+οἴ->ói
+αν->an
+ον->on
+ν->n
+εἱ->hei
+ού->ú
+οὖ->u
+οὐ->u
+αῖ->ai
+αι->ai
+αί->ái
+αί->ái
+αὶ->ái
+αἱ->ai
+αυ->au
+αύ->áu
+αὺ->áu
+αῦ->áu
+ει->e
+εί->éi
+εὶ->éi
+εί->ey
+ευ->eu
+εύ->éu
+εύ->éu
+εὺ->éu
+οι->oi
+οί->ói
+οί->ói
+οὶ->ói
+οἱ->hoi
+ου->u
+ού->ú
+οὺ->ú
+ηυ->eu
+ηύ->óu
+ηὺ->óu
+υι->ui
+υί->úi
+υὶ->úi
+υ->u
+ἀ->a
+ἁ->ha
+ἂ->á
+ἃ->há
+ἄ->á
+ἅ->há
+ἆ->a
+ἇ->ha
+Ἀ->a
+Ἁ->Ha
+Ἂ->á
+Ἃ->Ha
+Ἄ->á
+Ἅ->Ha
+Ἆ->á
+Ἇ->Ha
+ἐ->e
+ἑ->hey
+ἒ->é
+ἓ->hé
+ἔ->é
+ἕ->hé
+Ἐ->é
+Ἑ->he
+Ἒ->é
+Ἓ->Hé
+Ἔ->é
+Ἕ->Hé
+ἠ->E
+ἡ->he
+ἢ->é
+ἣ->hé
+ἤ->é
+ἥ->hé
+ἦ->e
+ἧ->hé
+Ἠ->E
+Ἡ->he
+Ἢ->é
+Ἣ->hé
+Ἤ->é
+Ἥ->hé
+Ἦ->E
+Ἧ->hé
+ἰ->i
+ἱ->hi
+ἲ->í
+ἳ->hí
+ἴ->í
+ἵ->hí
+ἶ->i
+ἷ->hí
+Ἰ->i
+Ἱ->Hi
+Ἲ->í
+Ἳ->Hí
+Ἴ->í
+Ἵ->Hí
+Ἶ->i
+Ἷ->Hí
+ὀ->o
+ὁ->ho
+ὂ->ó
+ὃ->ho
+ὄ->ó
+ὅ->ho
+Ὀ->o
+Ὁ->ho
+Ὂ->ó
+Ὃ->ho
+Ὄ->ó
+Ὅ->ho
+ὐ->u
+ὑ->hu
+ὒ->ú
+ὓ->hu
+ὔ->ú
+ὕ->hu
+ὖ->u
+ὗ->hu
+Ὑ->Hu
+Ὓ->ú
+Ὕ->ú
+Ὗ->Hu
+ὠ->o
+ὡ->ho
+ὢ->ó
+ὣ->hó
+ὤ->ó
+ὥ->hó
+ὦ->o
+ὧ->hó
+Ὠ->o
+Ὡ->ho
+Ὢ->ó
+Ὣ->ho
+Ὤ->ó
+Ὥ->hó
+Ὦ->o
+Ὧ->hó
+ὰ->á
+ά->á
+ὲ->é
+έ->é
+ὴ->é
+ή->é
+ὶ->i
+ί->í
+ὸ->ó
+ό->ó
+ὺ->ú
+ύ->ú
+ὼ->ó
+ώ->ó
+ᾀ->ai
+ᾁ->hai
+ᾂ->ái
+ᾃ->hái
+ᾄ->ái
+ᾅ->hái
+ᾆ->ai
+ᾇ->hái
+ᾈ->Ai
+ᾉ->hai
+ᾊ->ái
+ᾋ->hái
+ᾌ->ái
+ᾍ->hái
+ᾎ->ái
+ᾏ->hái
+ᾐ->ei
+ᾑ->hai
+ᾒ->éi
+ᾓ->hái
+ᾔ->éi
+ᾕ->hái
+ᾖ->ei
+ᾗ->hái
+ᾘ->ei
+ᾙ->he
+ᾚ->éi
+ᾛ->hé
+ᾜ->éi
+ᾝ->hé
+ᾞ->ei
+ᾟ->hé
+ᾠ->oi
+ᾡ->hoi
+ᾢ->ói
+ᾣ->hói
+ᾤ->ói
+ᾥ->hói
+ᾦ->oi
+ᾧ->hói
+ᾨ->oi
+ᾩ->hoi
+ᾪ->oi
+ᾫ->hói
+ᾬ->ói
+ᾭ->hói
+ᾮ->ói
+ᾯ->hói
+ᾰ->a
+ᾱ->a
+ᾲ->ái
+ᾳ->ai
+ᾴ->ái
+ᾶ->a
+ᾷ->ái
+Ᾰ->á
+Ᾱ->A
+Ὰ->A
+Ά->Ha
+ᾼ->Ai
+ῂ->éy
+ῃ->ey
+ῄ->éy
+ῆ->éy
+ῇ->éy
+Ὲ->He
+Έ->E
+Ὴ->Hay
+Ή->Ei
+ῌ->Ei
+ῐ->í
+ῑ->i
+ῒ->í
+ΐ->i
+ῖ->í
+ῗ->í
+Ῐ->í
+Ῑ->I
+Ὶ->Hee
+Ί->I
+ῠ->U
+ῡ->u
+ῢ->ú
+ΰ->ú
+ῤ->r
+ῥ->r
+ῦ->ú
+ῧ->ú
+Ῠ->ú
+Ῡ->U
+Ὺ->U
+Ύ->Hu
+Ῥ->R
+ῲ->ó
+ῳ->oi
+ῴ->ói
+ῶ->ó
+ῷ->ói
+Ὸ->O
+Ό->Ho
+Ὼ->Ho
+Ώ->O
+ῼ->Oi
+ή->é
+η->e
+αu->au
+ύ->u
+ηὐ->eu

convert.py

@@ -0,0 +1,13 @@
+if __name__ == "__main__":
+    with open("ancient-greek-phonemes.txt", "r") as mapping_file:
+        mapping = dict(
+            [(ancient_greek, latin) for ancient_greek, latin in [line.rstrip().split("->") for line in mapping_file.readlines()]]
+        )
+    with open("original.txt", "r") as book_txt:
+        book = book_txt.read()
+
+    for key, value in mapping.items():
+        book = book.replace(key, value)
+
+    with open("converted.txt", "w") as book_txt:
+        book_txt.write(book)