update

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.far filter=lfs diff=lfs merge=lfs -text
+*.utf8 filter=lfs diff=lfs merge=lfs -text

dict/README.md

@@ -0,0 +1,31 @@
+# CppJieba字典
+
+文件后缀名代表的是词典的编码方式。
+比如filename.utf8 是 utf8编码，filename.gbk 是 gbk编码方式。
+
+
+## 分词
+
+### jieba.dict.utf8/gbk
+
+作为最大概率法(MPSegment: Max Probability)分词所使用的词典。
+
+### hmm_model.utf8/gbk
+
+作为隐式马尔科夫模型(HMMSegment: Hidden Markov Model)分词所使用的词典。
+
+__对于MixSegment(混合MPSegment和HMMSegment两者)则同时使用以上两个词典__
+
+
+## 关键词抽取
+
+### idf.utf8
+
+IDF(Inverse Document Frequency)
+在KeywordExtractor中，使用的是经典的TF-IDF算法，所以需要这么一个词典提供IDF信息。
+
+### stop_words.utf8
+
+停用词词典
+
+

dict/hmm_model.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f17790586ac86dd048c8adffed052c4bd2b28ed0682972c1275e59040c0589a7
+size 519739

dict/idf.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbd1e03d72b2263cc8d84a4304ed77677eed9e7deaf43a1a5133bbba9733b535
+size 5998717

dict/jieba.dict.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3043b77068e09c9904f27cad82f12b6ebe9dbdb5aeff3b25e45ab7f9c1122b55
+size 5071204

dict/pos_dict/char_state_tab.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28b7be1dd7369766a51445af4d42e9a2ba4bf374c13be5bc1ca7721e27271dbb
+size 327139

dict/pos_dict/prob_emit.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c33c4cb7edf3b3a5947df7209b6e9f267eae1f21335d9e2bd2521ea07105457a
+size 1687686

dict/pos_dict/prob_start.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13623ea0e9300bdb597cb2da28770b7b385d6c0098d66e516083fb01b6bd5d96
+size 4347

dict/pos_dict/prob_trans.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f22363e2307408293d180c6f9f6b5cb75879d52f722f7764fa2d3d0ae2400236
+size 124159

dict/stop_words.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b788b8a939d2e2fe079abd579ea98f12f9fb84370bfd0dddd81bb9381f7ab42c
+size 8974

dict/user.dict.utf8

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495bbf49270408a1234690e1e6a97328f30a482a7a72aa769e8a12e8714b0c62
+size 49

lexicon.txt

@@ -21285,6 +21285,7 @@
 頻 
 恵 
 𤋮 
+kaldi k ʰ a ↓ ↑ ə ɹ ` ↓ ↑ t ⁼ i ↑
 阿胶 ə ↓ ʧ ⁼ y a u →
 挨打 a i ↑ t ⁼ a ↓ ↑
 拗口 a u ↓ k ʰ o u ↓ ↑
@@ -21302,6 +21303,21 @@
 屏气 p ⁼ i N g ↓ ↑ ʧ ʰ i ↓
 屏住 p ⁼ i N g ↓ ↑ ʦ ` ⁼ u ↓
 漂泊 p ʰ y a u → p ⁼ w o ↑
+淡泊 t ⁼ a N N ↓ p ⁼ w o ↑
+晚泊 w a N N ↓ ↑ p ⁼ w o ↑
+憩泊 ʧ ʰ i ↓ p ⁼ w o ↑
+夜泊 y e ↓ p ⁼ w o ↑
+泊船 p ⁼ w o ↑ ʦ ` ʰ w a N N ↑
+船泊 ʦ ` ʰ w a N N ↑ p ⁼ w o ↑
+泊舟 p ⁼ w o ↑ ʦ ` ⁼ o u →
+泊步 p ⁼ w o ↑ p ⁼ u ↓
+泊主 p ⁼ w o ↑ ʦ ` ⁼ u ↓ ↑
+泊车 p ⁼ w o ↑ ʦ ` ʰ ə →
+泊位 p ⁼ w o ↑ w e i ↓
+泊如 p ⁼ w o ↑ ɹ ` u ↑
+泊礼 p ⁼ w o ↑ l i ↓ ↑
+厚泊 h o u ↓ p ⁼ w o ↑
+停位 t ʰ i N g ↑ w e i ↓
 曝光 p ⁼ a u ↓ k ⁼ w a N g →
 长江 ʦ ` ʰ a N g ↑ ʧ ⁼ y a N g →
 长短 ʦ ` ʰ a N g ↑ t ⁼ w a N N ↓ ↑
@@ -21439,7 +21455,7 @@
 都雅 t ⁼ u → y a ↓ ↑
 都会 t ⁼ u → h w e i ↓
 都为一集 t ⁼ u → w e i ↓ i → ʧ ⁼ i ↑
-都卿相 t ⁼ u → ʧ ʰ i N g → ʃ y a N g →
+都卿相 t ⁼ u → ʧ ʰ i N g → ʃ y a N g ↓
 上当 s ` a N g ↓ t ⁼ a N g ↓
 当铺 t ⁼ a N g ↓ p ʰ u ↓
 弹射 t ʰ a N N ↑ s ` ə ↓
@@ -21601,6 +21617,7 @@
 几乎 ʧ ⁼ i → h u →
 考卷 k ʰ a u ↓ ↑ ʧ ⁼ ɥ a N N ↓
 试卷 s ` ɹ ` ↓ ʧ ⁼ ɥ a N N ↓
+答卷 t ⁼ a ↑ ʧ ⁼ ɥ a N N ↓
 倔强 ʧ ⁼ ɥ e ↑ ʧ ⁼ y a N g ↓
 强嘴 ʧ ⁼ y a N g ↓ ʦ ⁼ w e i ↓ ↑
 校对 ʧ ⁼ y a u ↓ t ⁼ w e i ↓
@@ -21720,6 +21737,34 @@
 失调 s ` ɹ ` → t ʰ y a u ↑
 可恶 k ʰ ə ↓ ↑ u ↓
 厌恶 y e N N ↓ u ↓
+相貌 ʃ y a N g ↓ m a u ↓
+照相 ʦ ` ⁼ a u ↓ ʃ y a N g ↓
+凶相 ʃ y u N g → ʃ y a N g ↓
+可怜相 k ʰ ə ↓ ↑ l y e N N ↑ ʃ y a N g ↓
+月相 ɥ e ↓ ʃ y a N g ↓
+金相 ʧ ⁼ i N N → ʃ y a N g ↓
+相面 ʃ y a N g ↓ m y e N N ↓
+相术 ʃ y a N g ↓ s ` u ↓
+相扑 ʃ y a N g ↓ p ʰ u →
+相声 ʃ y a N g ↓ s ` ə N g →
+相士 ʃ y a N g ↓ s ` ɹ ` ↓
+相体裁衣 ʃ y a N g ↓ t ʰ i ↓ ↑ ʦ ʰ a i ↑ i →
+相册 ʃ y a N g ↓ ʦ ʰ ə ↓
+相图 ʃ y a N g ↓ t ʰ u ↑
+相纸 ʃ y a N g ↓ ʦ ` ⁼ ɹ ` ↓ ↑
+相公 ʃ y a N g ↓ k ⁼ u N g →
+相君 ʃ y a N g ↓ ʧ ⁼ ɥ ə N N →
+相机 ʃ y a N g ↓ ʧ ⁼ i →
+相里 ʃ y a N g ↓ l i ↓ ↑
+相马 ʃ y a N g ↓ m a ↓ ↑
+丞相 ʦ ` ʰ ə N g ↑ ʃ y a N g ↓
+辅相 f u ↓ ↑ ʃ y a N g ↓
+宰相 ʦ ⁼ a i ↓ ↑ ʃ y a N g ↓
+首相 s ` o u ↓ ↑ ʃ y a N g ↓
+相态 ʃ y a N g ↓ t ʰ a i ↓
+相角 ʃ y a N g ↓ ʧ ⁼ y a u ↓ ↑
+相位 ʃ y a N g ↓ w e i ↓
+看相 k ʰ a N N ↓ ʃ y a N g ↓
 高兴 k ⁼ a u → ʃ i N g ↓
 兴致勃勃 ʃ i N g ↓ ʦ ` ⁼ ɹ ` ↓ p ⁼ w o ↑ p ⁼ w o ↑
 兴奋 ʃ i N g → f ə N N ↓
@@ -21735,6 +21780,7 @@
 音乐 i N N → ɥ e ↓
 乐曲 ɥ e ↓ ʧ ʰ ɥ →
 自怨自艾 ʦ ⁼ ɹ ↓ ɥ a N N ↓ ʦ ⁼ ɹ ↓ i ↓
+委蛇 w e i ↓ ↑ i ↑
 朝气 ʦ ` ⁼ a u → ʧ ʰ i ↓
 着数 ʦ ` ⁼ a u → s ` u ↓
 中国 ʦ ` ⁼ u N g → k ⁼ w o ↑

rule.far

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b090ed05e333fe125b62d8b1de5f1a1d4579fb237c606e7ac0b84707c863a01f
+size 180717014

vits-hf-zh-jp-zomehwh.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27bcec3bbd0a9b3bcddf355161f52c66f631f04ec538edb76771c79c926d4eb4
-size 121899981
+oid sha256:227f68cec4ee79e80845b2f7bbb9f9f654b95cab1d69be54e78af46c33e07935
+size 121899993