From 27cb54da4fb778b5d858f694fc7f6f4c9de5e970 Mon Sep 17 00:00:00 2001
From: tuna2134 <masato@priv.tuna2134.dev>
Date: Tue, 10 Sep 2024 00:20:34 +0000
Subject: [PATCH] fixed

---
 sbv2_core/src/main.rs | 8 ++++----
 sbv2_core/src/norm.rs | 9 ++++++++-
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/sbv2_core/src/main.rs b/sbv2_core/src/main.rs
index 9a0f7ab..046c31f 100644
--- a/sbv2_core/src/main.rs
+++ b/sbv2_core/src/main.rs
@@ -1,14 +1,14 @@
-use sbv2_core::{bert, error, jtalk};
+use sbv2_core::{bert, error, jtalk, nlp, norm};
 
 fn main() -> error::Result<()> {
     let text = "こんにちは,世界!";
 
-    let normalized_text = jtalk::normalize_text(text);
+    let normalized_text = norm::normalize_text(text);
     println!("{}", normalized_text);
 
     let jtalk = jtalk::JTalk::new()?;
-    let (phones, tones, _) = jtalk.g2p(&normalized_text)?;
-    println!("{:?}", tones);
+    let (phones, tones, word2ph) = jtalk.g2p(&normalized_text)?;
+    let (phones, tones, lang_ids) = nlp::cleaned_text_to_sequence(phones, tones);
 
     let tokenizer = jtalk::get_tokenizer()?;
     println!("{:?}", tokenizer);
diff --git a/sbv2_core/src/norm.rs b/sbv2_core/src/norm.rs
index 5139427..7897d57 100644
--- a/sbv2_core/src/norm.rs
+++ b/sbv2_core/src/norm.rs
@@ -69,6 +69,13 @@ __PUNCTUATION_CLEANUP_PATTERN = re.compile(
 )
 */
 
+pub const ZH_SYMBOLS: [&str; 65] = [
+    "E", "En", "a", "ai", "an", "ang", "ao", "b", "c", "ch", "d", "e", "ei", "en", "eng", "er",
+    "f", "g", "h", "i", "i0", "ia", "ian", "iang", "iao", "ie", "in", "ing", "iong", "ir", "iu",
+    "j", "k", "l", "m", "n", "o", "ong", "ou", "p", "q", "r", "s", "sh", "t", "u", "ua", "uai",
+    "uan", "uang", "ui", "un", "uo", "v", "van", "ve", "vn", "w", "x", "y", "z", "zh", "AA", "EE",
+    "OO",
+];
 pub const JP_SYMBOLS: [&str; 42] = [
     "N", "a", "a:", "b", "by", "ch", "d", "dy", "e", "e:", "f", "g", "gy", "h", "hy", "i", "i:",
     "j", "k", "ky", "m", "my", "n", "ny", "o", "o:", "p", "py", "q", "r", "ry", "s", "sh", "t",
@@ -83,7 +90,7 @@ pub static PUNCTUATION_SYMBOLS: Lazy<Vec<&str>> = Lazy::new(|| {
 });
 const PAD: &str = "_";
 pub static SYMBOLS: Lazy<Vec<&str>> = Lazy::new(|| {
-    let mut symbols = JP_SYMBOLS.to_vec();
+    let mut symbols = vec![PAD];
     symbols.append(&mut JP_SYMBOLS.to_vec());
     symbols.append(&mut PUNCTUATION_SYMBOLS.to_vec());
     symbols