mmcauliffe commited on
Commit
bfe85af
·
verified ·
1 Parent(s): da71f86

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -37,3 +37,4 @@ acoustic/final.alimdl filter=lfs diff=lfs merge=lfs -text
37
  acoustic/final.mdl filter=lfs diff=lfs merge=lfs -text
38
  acoustic/tree filter=lfs diff=lfs merge=lfs -text
39
  g2p/japanese_mfa/model.fst filter=lfs diff=lfs merge=lfs -text
 
 
37
  acoustic/final.mdl filter=lfs diff=lfs merge=lfs -text
38
  acoustic/tree filter=lfs diff=lfs merge=lfs -text
39
  g2p/japanese_mfa/model.fst filter=lfs diff=lfs merge=lfs -text
40
+ g2p/japanese_katakana_mfa/model.fst filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -77,8 +77,8 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
77
  - **Source:** wikipron
78
  - **Orthography:** Kanji and kana
79
  - **Phone set:** MFA
80
- - **Words:** 2,239,777
81
- * **Phones:** 78
82
  * **Graphemes:** 5,752
83
 
84
  ##### IPA chart
@@ -90,7 +90,7 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
90
  | **Nasal** | m mː | | n nː | ɲ ɲː | ŋ | ɴ ɴː | |
91
  | Palatalized | mʲ mʲː | | | | | | |
92
  | **Stop** | p pː b bː | | t tː d dː | c cː ɟ ɟː | k kː ɡ ɡː | | ʔ|
93
- | Palatalized | pʲ pʲː bʲ | | tʲ tʲː dʲ dʲː | | | | |
94
  | **Affricate** | | | ts tsː dz dzː | tɕ tɕː dʑ dʑː | | | |
95
  | **Sibilant** | | | s sː z | ɕ ɕː ʑ | | | |
96
  | **Fricative** | ɸ ɸː | v | | ç | | | h hː|
@@ -122,26 +122,24 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
122
  - **Source:** https://voice.mozilla.org/en/datasets
123
  - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
124
  - **Dialects:** N/A
125
- - **Number of hours:** 71.54
126
- - **Number of utterances:** 56,631
127
- - **Number of speakers:** 1,364
128
- - **Female speakers:** 199
129
- - **Male speakers:** 459
130
- - **Unknown speakers:** 706
131
-
132
 
133
  #### GlobalPhone Japanese
134
 
135
  - **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0199/
136
  - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
137
  - **Dialects:** N/A
138
- - **Number of hours:** 33.88
139
- - **Number of utterances:** 13,103
140
  - **Number of speakers:** 144
141
  - **Female speakers:** 44
142
  - **Male speakers:** 104
143
- - **Unknown speakers:** 0
144
-
145
 
146
  #### Japanese Versatile Speech
147
 
@@ -149,13 +147,12 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
149
  - **License:** [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)
150
  - **Dialects:** N/A
151
  - **Number of hours:** 30.25
152
- - **Number of utterances:** 14,994
153
- - **Number of speakers:** 100
154
  - **Female speakers:** 51
155
  - **Male speakers:** 49
156
  - **Unknown speakers:** 100
157
 
158
-
159
  #### LaboroTV Japanese
160
 
161
  - **Source:** https://laboro.ai/activity/column/engineer/eg-laboro-tv-corpus-jp/
@@ -168,7 +165,6 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
168
  - **Male speakers:** 0
169
  - **Unknown speakers:** 305,246
170
 
171
-
172
  #### MagicData ASR-SJapDuSC
173
 
174
  - **Source:** https://magichub.com/datasets/japanese-scripted-speech-corpus-daily-use-sentence/
@@ -181,7 +177,6 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
181
  - **Male speakers:** 19
182
  - **Unknown speakers:** 0
183
 
184
-
185
  #### Microsoft Speech Language Translation Japanese
186
 
187
  - **Source:** https://msropendata.com/datasets/54813518-4ea6-4c39-9bb2-b0d1e5f0c187
@@ -194,20 +189,18 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
194
  - **Male speakers:** 0
195
  - **Unknown speakers:** 112
196
 
197
-
198
  #### TEDxJP-10K
199
 
200
  - **Source:** https://github.com/laboroai/TEDxJP-10K
201
  - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
202
  - **Dialects:** N/A
203
- - **Number of hours:** 8.85
204
- - **Number of utterances:** 9,962
205
  - **Number of speakers:** 271
206
  - **Female speakers:** 0
207
  - **Male speakers:** 0
208
  - **Unknown speakers:** 271
209
 
210
-
211
  ### Training Procedure
212
 
213
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
77
  - **Source:** wikipron
78
  - **Orthography:** Kanji and kana
79
  - **Phone set:** MFA
80
+ - **Words:** 2,224,242
81
+ * **Phones:** 77
82
  * **Graphemes:** 5,752
83
 
84
  ##### IPA chart
 
90
  | **Nasal** | m mː | | n nː | ɲ ɲː | ŋ | ɴ ɴː | |
91
  | Palatalized | mʲ mʲː | | | | | | |
92
  | **Stop** | p pː b bː | | t tː d dː | c cː ɟ ɟː | k kː ɡ ɡː | | ʔ|
93
+ | Palatalized | pʲ pʲː bʲ | | tʲ tʲː dʲ | | | | |
94
  | **Affricate** | | | ts tsː dz dzː | tɕ tɕː dʑ dʑː | | | |
95
  | **Sibilant** | | | s sː z | ɕ ɕː ʑ | | | |
96
  | **Fricative** | ɸ ɸː | v | | ç | | | h hː|
 
122
  - **Source:** https://voice.mozilla.org/en/datasets
123
  - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
124
  - **Dialects:** N/A
125
+ - **Number of hours:** 118.95
126
+ - **Number of utterances:** 89,100
127
+ - **Number of speakers:** 3,109
128
+ - **Female speakers:** 702
129
+ - **Male speakers:** 1,120
130
+ - **Unknown speakers:** 1,285
 
131
 
132
  #### GlobalPhone Japanese
133
 
134
  - **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0199/
135
  - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
136
  - **Dialects:** N/A
137
+ - **Number of hours:** 33.87
138
+ - **Number of utterances:** 13,111
139
  - **Number of speakers:** 144
140
  - **Female speakers:** 44
141
  - **Male speakers:** 104
142
+ - **Unknown speakers:** 1
 
143
 
144
  #### Japanese Versatile Speech
145
 
 
147
  - **License:** [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)
148
  - **Dialects:** N/A
149
  - **Number of hours:** 30.25
150
+ - **Number of utterances:** 15,045
151
+ - **Number of speakers:** 400
152
  - **Female speakers:** 51
153
  - **Male speakers:** 49
154
  - **Unknown speakers:** 100
155
 
 
156
  #### LaboroTV Japanese
157
 
158
  - **Source:** https://laboro.ai/activity/column/engineer/eg-laboro-tv-corpus-jp/
 
165
  - **Male speakers:** 0
166
  - **Unknown speakers:** 305,246
167
 
 
168
  #### MagicData ASR-SJapDuSC
169
 
170
  - **Source:** https://magichub.com/datasets/japanese-scripted-speech-corpus-daily-use-sentence/
 
177
  - **Male speakers:** 19
178
  - **Unknown speakers:** 0
179
 
 
180
  #### Microsoft Speech Language Translation Japanese
181
 
182
  - **Source:** https://msropendata.com/datasets/54813518-4ea6-4c39-9bb2-b0d1e5f0c187
 
189
  - **Male speakers:** 0
190
  - **Unknown speakers:** 112
191
 
 
192
  #### TEDxJP-10K
193
 
194
  - **Source:** https://github.com/laboroai/TEDxJP-10K
195
  - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
196
  - **Dialects:** N/A
197
+ - **Number of hours:** 8.87
198
+ - **Number of utterances:** 9,954
199
  - **Number of speakers:** 271
200
  - **Female speakers:** 0
201
  - **Male speakers:** 0
202
  - **Unknown speakers:** 271
203
 
 
204
  ### Training Procedure
205
 
206
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
acoustic/final.alimdl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39a380193a765f1fa5e9992375d2b92aa1814888ef11f3a0410090cce376cd0b
3
- size 50239066
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2618fa1ff80a5a3816a1fece7b4d2f03d92fa0a1b965b11ef9e40f40e8574604
3
+ size 50236066
acoustic/final.mdl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c8e0df5b38d52a2fb83447faf152e68c637d18c0d7eb6fd410a21763d6efa5b
3
- size 50239066
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f0a1ae8d8df8cd4adb68f14c86ed1f3718bae3e7057363751470ad0572c664f
3
+ size 50236066
acoustic/lda.mat CHANGED
Binary files a/acoustic/lda.mat and b/acoustic/lda.mat differ
 
acoustic/meta.json CHANGED
@@ -1 +1 @@
1
- {"phones": ["a", "aː", "b", "bʲ", "bʲː", "bː", "c", "cː", "d", "dz", "dzː", "dʑ", "dʑː", "dʲ", "dʲː", "dː", "e", "eː", "h", "hː", "i", "iː", "i̥", "j", "k", "kː", "m", "mʲ", "mʲː", "mː", "n", "nː", "o", "oː", "p", "pʲ", "pʲː", "pː", "s", "sː", "t", "ts", "tsː", "tɕ", "tɕː", "tʲ", "tʲː", "tː", "v", "vʲ", "w", "wː", "z", "ç", "çː", "ŋ", "ɕ", "ɕː", "ɟ", "ɟː", "ɡ", "ɡː", "ɨ", "ɨː", "ɨ̥", "ɯ", "ɯː", "ɯ̥", "ɰ̃", "ɲ", "ɲː", "ɴ", "ɴː", "ɸ", "ɸʲ", "ɸʲː", "ɸː", "ɾ", "ɾʲ", "ɾʲː", "ɾː", "ʑ", "ʔ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "aː": 4, "b": 5, "bʲ": 6, "bʲː": 7, "bː": 8, "c": 9, "cː": 10, "d": 11, "dz": 12, "dzː": 13, "dʑ": 14, "dʑː": 15, "dʲ": 16, "dʲː": 17, "dː": 18, "e": 19, "eː": 20, "h": 21, "hː": 22, "i": 23, "iː": 24, "i̥": 25, "j": 26, "k": 27, "kː": 28, "m": 29, "mʲ": 30, "mʲː": 31, "mː": 32, "n": 33, "nː": 34, "o": 35, "oː": 36, "p": 37, "pʲ": 38, "pʲː": 39, "pː": 40, "s": 41, "sː": 42, "t": 43, "ts": 44, "tsː": 45, "tɕ": 46, "tɕː": 47, "tʲ": 48, "tʲː": 49, "tː": 50, "v": 51, "vʲ": 52, "w": 53, "wː": 54, "z": 55, "ç": 56, "çː": 57, "ŋ": 58, "ɕ": 59, "ɕː": 60, "ɟ": 61, "ɟː": 62, "ɡ": 63, "ɡː": 64, "ɨ": 65, "ɨː": 66, "ɨ̥": 67, "ɯ": 68, "ɯː": 69, "ɯ̥": 70, "ɰ̃": 71, "ɲ": 72, "ɲː": 73, "ɴ": 74, "ɴː": 75, "ɸ": 76, "ɸʲ": 77, "ɸʲː": 78, "ɸː": 79, "ɾ": 80, "ɾʲ": 81, "ɾʲː": 82, "ɾː": 83, "ʑ": 84, "ʔ": 85}, "phone_groups": {"0": ["p", "pː"], "1": ["pʲ", "pʲː"], "2": ["b", "bː", "v"], "3": ["bʲ", "bʲː", "vʲ"], "4": ["t", "tʲ", "tʲː", "tː"], "5": ["d", "dʲ", "dʲː", "dː"], "6": ["tɕ", "tɕː"], "7": ["ɕ", "ɕː"], "8": ["s", "sː"], "9": ["ts", "tsː"], "10": ["dz", "dzː", "z"], "11": ["dʑ", "dʑː", "ʑ"], "12": ["ɾ", "ɾː"], "13": ["ɾʲ", "ɾʲː"], "14": ["ŋ", "ɰ̃", "ɴ", "ɴː"], "15": ["m", "mː"], "16": ["mʲ", "mʲː"], "17": ["n", "nː"], "18": ["ɲ", "ɲː"], "19": ["ɟ", "ɟː"], "20": ["ɡ", "ɡː"], "21": ["c", "cː"], "22": ["k", "kː"], "23": ["h", "hː", "ç", "çː", "ɸ", "ɸʲ", "ɸʲː", "ɸː"], "24": ["a", "aː"], "25": ["i", "iː", "i̥"], "26": ["j"], "27": ["e", "eː"], "28": ["ɯ", "ɯː", "ɯ̥"], "29": ["ɨ", "ɨː", "ɨ̥"], "30": ["w", "wː"], "31": ["o", "oː"], "32": ["ʔ"]}, "version": "3.3.0", "architecture": "gmm-hmm", "train_date": "2026-05-20 23:53:47.161847", "training": {"audio_duration": 1598071.6044385151, "num_speakers": 309319, "num_utterances": 329938, "num_oovs": 0, "average_log_likelihood": -53.97496903390072}, "dictionaries": {"names": ["japanese_mfa"], "default": "japanese_mfa", "silence_word": "<eps>", "oov_word": "<unk>", "bracketed_word": "[bracketed]", "laughter_word": "[laughter]", "clitic_marker": "'", "position_dependent_phones": false}, "language": "japanese", "tokenization": "ja", "features": {"type": "mfcc", "use_energy": false, "frame_shift": 10, "frame_length": 25, "snip_edges": false, "low_frequency": 20, "high_frequency": 7800, "sample_frequency": 16000, "dither": 0.0, "energy_floor": 0.0, "num_coefficients": 13, "num_mel_bins": 23, "cepstral_lifter": 22, "preemphasis_coefficient": 0.97, "uses_cmvn": true, "uses_deltas": true, "uses_voiced": false, "uses_splices": false, "uses_speaker_adaptation": true, "use_pitch": false, "use_voicing": false, "min_f0": 50, "max_f0": 800, "delta_pitch": 0.005, "penalty_factor": 0.1, "silence_weight": 0.0, "splice_left_context": 3, "splice_right_context": 3}, "oov_phone": "spn", "optional_silence_phone": "sil", "phone_set_type": "UNKNOWN", "silence_probability": 0.2, "initial_silence_probability": 0.2, "final_silence_correction": 0.99, "final_non_silence_correction": 0.23, "duration_information": {"dʲː": [0.12700000144541262, 0.027100639238464758], "mʲ": [0.06701977258215586, 0.025340541937095926], "mʲː": [0.10267125732773905, 0.05261071010488478], "n": [0.057125297481895994, 0.04837945111971778], "ɴ": [0.09444440589919609, 0.11891175856372534], "ɲ": [0.0617512645890135, 0.03872344803028485], "nː": [0.10383094645624619, 0.045045977252875694], "ɲː": [0.11670010113388742, 0.04137576654825047], "ŋ": [0.07806834034506696, 0.03245500681479054], "o": [0.06543697360489922, 0.046350813573996744], "oː": [0.061648058560308, 0.06813675461858536], "p": [0.07941039646437428, 0.03338038888084108], "ɸ": [0.0791059018464695, 0.06537037625495395], "pː": [0.1361203854029768, 0.05368862615594444], "ɸː": [0.13636466454375873, 0.04581721578228687], "pʲ": [0.08323257258737095, 0.036985457211858724], "tː": [0.13115083622713472, 0.0534517619903759], "tɕ": [0.09911046049323825, 0.03742817848768125], "tɕː": [0.13564579069876082, 0.056349993063220846], "tʲ": [0.08869391049374827, 0.029625097349498305], "tʲː": [0.14500000265737376, 0.06014472664322222], "ts": [0.09226881321104427, 0.035224333625233646], "tsː": [0.13249724261738635, 0.050822561822374955], "v": [0.06476385973669298, 0.022275303120366092], "vʲ": [0.07368421482171124, 0.023018843120109704], "w": [0.06036593010020435, 0.026912313709912452], "z": [0.06637348466094166, 0.022684617745210158], "a": [0.07172855057569456, 0.05367569748494782], "aː": [0.1653995340442872, 0.12494450472198171], "ɯ": [0.06147057323243353, 0.04787310962653594], "ɰ̃": [0.07917007597859436, 0.03285579024545734], "ɯ̥": [0.052400286439331804, 0.037642880212900034], "mː": [0.11900318409479446, 0.04101577618549635], "ɯː": [0.133714942050549, 0.09294571383926024], "ɴː": [0.5245901487034852, 0.44320147864856607], "ɸʲ": [0.08850065570277237, 0.030534600163103286], "pʲː": [0.16040001164018003, 0.059435103837879276], "ɸʲː": [0.12499997019767761, 0.0353554317823941], "ɾ": [0.04668684173398758, 0.015380733435455396], "ɾʲ": [0.051219813511571566, 0.019246690252237776], "s": [0.0965333568797266, 0.05626395802276678], "sː": [0.16046288031730113, 0.1916570109346676], "t": [0.06933436958549147, 0.028722540757703308], "b": [0.060784183683027335, 0.02256226576554672], "bʲ": [0.06885036893988243, 0.023009059968321727], "c": [0.05965485509810899, 0.11382968845435097], "ç": [0.0806034645627951, 0.037157394632713475], "ɕ": [0.09535515447927907, 0.038164742106634314], "cː": [0.13829073480087947, 0.06417569347878448], "ɕː": [0.14815911208821791, 0.04850224480501888], "d": [0.06053624121725925, 0.10940655257313303], "dː": [0.14339051500112032, 0.032513125549875614], "dʲ": [0.06929515694051774, 0.030371524142653872], "dz": [0.07472161777922254, 0.025936553478004745], "dʑ": [0.07862906413094069, 0.028019001235701415], "dzː": [0.1281249162275344, 0.05341879767038914], "dʑː": [0.1368237811859429, 0.03672999866349392], "e": [0.07055533523771026, 0.06086837062240335], "eː": [0.13117863696648013, 0.07083261710136798], "ɡ": [0.037476260499196286, 0.05500229819497885], "ɡː": [0.12874977222293035, 0.06601995299724445], "h": [0.07321797286044851, 0.08435410619094488], "hː": [0.15690264659645284, 0.054838723103321205], "i": [0.051189077676273724, 0.04550793651365899], "ɨ": [0.05885101544815808, 0.08958502656896224], "i̥": [0.05318786479649406, 0.04160594666027455], "ɨ̥": [0.10169946046430638, 0.14719707924268943], "iː": [0.13548934607668042, 0.06853603039237988], "ɨː": [0.11367251063841276, 0.051294863273593824], "j": [0.06500234134335352, 0.03330936783263659], "ɟ": [0.07311051666265672, 0.02763836568288473], "ɟː": [0.17000000022706532, 0.0294174101399787], "k": [0.07566474750041795, 0.030341749933216925], "kː": [0.14536796591308046, 0.04923350538845851], "m": [0.0644281585850888, 0.02846024553675977], "ʑ": [0.06758147995828866, 0.023409502758463315], "ʔ": [0.07420319996189571, 0.06953912421748087]}}
 
1
+ {"phones": ["a", "aː", "b", "bʲ", "bʲː", "bː", "c", "cː", "d", "dz", "dzː", "dʑ", "dʑː", "dʲ", "dʲː", "dː", "e", "eː", "h", "hː", "i", "iː", "i̥", "j", "k", "kː", "m", "mʲ", "mʲː", "mː", "n", "nː", "o", "oː", "p", "pʲ", "pʲː", "pː", "s", "sː", "t", "ts", "tsː", "tɕ", "tɕː", "tʲ", "tʲː", "tː", "v", "vʲ", "w", "wː", "z", "ç", "çː", "ŋ", "ɕ", "ɕː", "ɟ", "ɟː", "ɡ", "ɡː", "ɨ", "ɨː", "ɨ̥", "ɯ", "ɯː", "ɯ̥", "ɰ̃", "ɲ", "ɲː", "ɴ", "ɴː", "ɸ", "ɸʲ", "ɸʲː", "ɸː", "ɾ", "ɾʲ", "ɾʲː", "ɾː", "ʑ", "ʔ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "aː": 4, "b": 5, "bʲ": 6, "bʲː": 7, "bː": 8, "c": 9, "cː": 10, "d": 11, "dz": 12, "dzː": 13, "dʑ": 14, "dʑː": 15, "dʲ": 16, "dʲː": 17, "dː": 18, "e": 19, "eː": 20, "h": 21, "hː": 22, "i": 23, "iː": 24, "i̥": 25, "j": 26, "k": 27, "kː": 28, "m": 29, "mʲ": 30, "mʲː": 31, "mː": 32, "n": 33, "nː": 34, "o": 35, "oː": 36, "p": 37, "pʲ": 38, "pʲː": 39, "pː": 40, "s": 41, "sː": 42, "t": 43, "ts": 44, "tsː": 45, "tɕ": 46, "tɕː": 47, "tʲ": 48, "tʲː": 49, "tː": 50, "v": 51, "vʲ": 52, "w": 53, "wː": 54, "z": 55, "ç": 56, "çː": 57, "ŋ": 58, "ɕ": 59, "ɕː": 60, "ɟ": 61, "ɟː": 62, "ɡ": 63, "ɡː": 64, "ɨ": 65, "ɨː": 66, "ɨ̥": 67, "ɯ": 68, "ɯː": 69, "ɯ̥": 70, "ɰ̃": 71, "ɲ": 72, "ɲː": 73, "ɴ": 74, "ɴː": 75, "ɸ": 76, "ɸʲ": 77, "ɸʲː": 78, "ɸː": 79, "ɾ": 80, "ɾʲ": 81, "ɾʲː": 82, "ɾː": 83, "ʑ": 84, "ʔ": 85}, "phone_groups": {"0": ["p", "pː"], "1": ["pʲ", "pʲː"], "2": ["b", "bː", "v"], "3": ["bʲ", "bʲː", "vʲ"], "4": ["t", "tʲ", "tʲː", "tː"], "5": ["d", "dʲ", "dʲː", "dː"], "6": ["tɕ", "tɕː"], "7": ["ɕ", "ɕː"], "8": ["s", "sː"], "9": ["ts", "tsː"], "10": ["dz", "dzː", "z"], "11": ["dʑ", "dʑː", "ʑ"], "12": ["ɾ", "ɾː"], "13": ["ɾʲ", "ɾʲː"], "14": ["ŋ", "ɰ̃", "ɴ", "ɴː"], "15": ["m", "mː"], "16": ["mʲ", "mʲː"], "17": ["n", "nː"], "18": ["ɲ", "ɲː"], "19": ["ɟ", "ɟː"], "20": ["ɡ", "ɡː"], "21": ["c", "cː"], "22": ["k", "kː"], "23": ["h", "hː", "ç", "çː", "ɸ", "ɸʲ", "ɸʲː", "ɸː"], "24": ["a", "aː"], "25": ["i", "iː", "i̥"], "26": ["j"], "27": ["e", "eː"], "28": ["ɯ", "ɯː", "ɯ̥"], "29": ["ɨ", "ɨː", "ɨ̥"], "30": ["w", "wː"], "31": ["o", "oː"], "32": ["ʔ"]}, "version": "3.4.3", "architecture": "gmm-hmm", "train_date": "2026-10-10 15:03:23.179761", "training": {"audio_duration": 1199747.3926113304, "num_speakers": 309319, "num_utterances": 242124, "num_oovs": 0, "average_log_likelihood": -53.721700343172046}, "dictionaries": {"names": ["japanese_mfa"], "default": "japanese_mfa", "silence_word": "<eps>", "oov_word": "<unk>", "bracketed_word": "[bracketed]", "laughter_word": "[laughter]", "clitic_marker": "'", "position_dependent_phones": false}, "language": "japanese", "tokenization": "ja", "features": {"type": "mfcc", "use_energy": false, "frame_shift": 10, "frame_length": 25, "snip_edges": false, "low_frequency": 20, "high_frequency": 7800, "sample_frequency": 16000, "dither": 0.0, "energy_floor": 0.0, "num_coefficients": 13, "num_mel_bins": 23, "cepstral_lifter": 22, "preemphasis_coefficient": 0.97, "uses_cmvn": true, "uses_deltas": true, "uses_voiced": false, "uses_splices": false, "uses_speaker_adaptation": true, "use_pitch": false, "use_voicing": false, "min_f0": 50, "max_f0": 800, "delta_pitch": 0.005, "penalty_factor": 0.1, "silence_weight": 0.0, "splice_left_context": 3, "splice_right_context": 3}, "oov_phone": "spn", "optional_silence_phone": "sil", "phone_set_type": "UNKNOWN", "silence_probability": 0.2, "initial_silence_probability": 0.2, "final_silence_correction": 0.99, "final_non_silence_correction": 0.24, "duration_information": {"tʲː": [-2.0162416181019545, 0.39014992662117937], "w": [-2.8708722754514224, 0.4072895037829683], "z": [-2.7497308982582727, 0.3317813105778213], "ç": [-2.5169448047392056, 0.43289489577233004], "ŋ": [-2.5947634758660203, 0.3447164123795913], "ɕ": [-2.3626317074901553, 0.3678118621249214], "ɕː": [-1.9478448284293477, 0.34597659209459164], "ɟ": [-2.659537261802714, 0.377925708370945], "ɟː": [-1.8253408430922964, 0.42259747804702735], "ɡ": [-3.1889527028920552, 0.6808466628056564], "ɡː": [-2.1148664521404474, 0.761746181202955], "ɨ": [-3.0032942719350855, 0.4037508749703049], "ɨː": [-2.2167184338669936, 0.4582185905279826], "ɨ̥": [-2.679688008594573, 0.5757362340922728], "ɯ": [-2.7723416476763267, 0.5064490062118696], "ɯː": [-2.1224952643660457, 0.5415828259755314], "ɯ̥": [-3.1005641654085787, 0.36817318529786813], "ɰ̃": [-2.586095813909079, 0.3898009917489517], "ɲ": [-2.814620691470968, 0.3925014077096929], "ɲː": [-2.1731689309278726, 0.3741657208523373], "ɴ": [-2.52266558669514, 0.4741488393137085], "ɴː": [-1.116349287894229, 1.3498537406784807], "ɸ": [-2.580534280858977, 0.43415361033173266], "ɸʲ": [-2.4489559747690106, 0.3618473411912869], "ɸʲː": [-2.099852896568074, 0.2867079704150915], "ɸː": [-2.004259852422173, 0.42164616984025266], "ɾ": [-3.6709628573799526, 0.7177945439104612], "ɾʲ": [-3.0098293589546463, 0.31981975736405327], "a": [-2.7143471332243263, 0.4535906542708324], "aː": [-1.9516760822255386, 0.48632782276640485], "b": [-2.8238923880295697, 0.3231381368369286], "bʲ": [-2.7081145342527218, 0.32048735842440296], "c": [-2.7835321964491335, 0.735188443948609], "oː": [-2.5485869515048507, 0.976166789431333], "p": [-2.5565420890747967, 0.35103076067829403], "pʲ": [-2.6363659742224965, 0.3731096319361902], "pʲː": [-1.8576212339152418, 0.4260370144303223], "pː": [-1.972607492788867, 0.39341829507620835], "s": [-2.30104104853272, 0.4519935387468075], "sː": [-1.5234385301264242, 1.2634860376947898], "t": [-2.67996336846013, 0.33620550238299995], "ts": [-2.3790545257319393, 0.348745857928197], "tsː": [-2.0417668890366505, 0.41584372898025107], "tɕ": [-2.319357081079195, 0.3509665190853381], "tɕː": [-1.9569583883950668, 0.43128848627376665], "tʲ": [-2.4707483393984857, 0.315763198302139], "tː": [-2.0320893580475414, 0.3930602723646268], "v": [-2.7809362214154616, 0.2862003840038777], "vʲ": [-2.616318916448208, 0.2835032182104879], "ʑ": [-2.7302486587140726, 0.34746007262955647], "ʔ": [-4.144984484573175, 0.8856107804079864], "cː": [-1.9740004745803423, 0.3948289763448585], "d": [-2.9739779398703794, 0.3291534466547461], "dz": [-2.6104301001231565, 0.31900517048990257], "dzː": [-2.088828106863989, 0.554407093109257], "dʑ": [-2.5948384199878083, 0.3389680943359212], "dʑː": [-2.0517178444850495, 0.3534986342047912], "dʲ": [-2.727070118755026, 0.29534414386644686], "dː": [-1.9800464215451972, 0.2701785993101523], "e": [-2.7998116339862564, 0.5105439160316249], "eː": [-2.094104063953231, 0.4123443771703535], "h": [-2.6207594203177007, 0.48534336658428273], "hː": [-1.8826136507905353, 0.2546349425969716], "i": [-2.881559501889971, 0.6101716241823957], "iː": [-2.0453239404502965, 0.4395064092727858], "i̥": [-3.02648972041764, 0.3600256398982755], "j": [-2.75854790084426, 0.41866159462260266], "k": [-2.5738668759299004, 0.35527717914513407], "kː": [-1.9603467542386865, 0.3603927049125921], "m": [-2.7500163784832496, 0.33113647372533467], "mʲ": [-2.6959925208289546, 0.33837910010020084], "mʲː": [-2.157751946253275, 0.428860212588672], "mː": [-2.1421797804011753, 0.34891325851036614], "n": [-2.91018866107937, 0.3726216433340153], "nː": [-2.253941487781602, 0.3594439565346149], "o": [-2.814305017103454, 0.4793634475177578]}}
acoustic/tree CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f53d9d1ba253d1740dcd8873b2aa45170639928aea9c6f1b5f71e45d852f0752
3
- size 377033
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808bfba1fbf4284d748fb62a118d05c5ef7324e30f08d7c3c13efa8d0991059f
3
+ size 388233
dictionary/japanese_mfa.dict CHANGED
The diff for this file is too large to render. See raw diff
 
dictionary/rules.yaml CHANGED
@@ -1,99 +1,99 @@
1
  dialects:
2
  us:
3
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
4
- non_silence_before_correction: 0.02
5
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
6
- probability: 0.13
7
  replacement: i̥
8
  segment: i
9
- silence_after_probability: 1.0
10
- silence_before_correction: -0.08
11
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
12
- non_silence_before_correction: 0.01
13
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
14
- probability: 0.24
15
  replacement: ''
16
  segment: i
17
- silence_after_probability: 1.07
18
- silence_before_correction: -0.07
19
  - following_context: $
20
- non_silence_before_correction: 0.05
21
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
22
- probability: 0.11
23
  replacement: i̥
24
  segment: i
25
- silence_after_probability: 0.07
26
- silence_before_correction: -0.19
27
  - following_context: $
28
- non_silence_before_correction: 0.07
29
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
30
- probability: 0.05
31
  replacement: ''
32
  segment: i
33
- silence_after_probability: 0.47
34
- silence_before_correction: -0.28
35
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
36
- non_silence_before_correction: 0.0
37
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
38
- probability: 0.27
39
  replacement: ɯ̥
40
  segment: ɯ
41
- silence_after_probability: 0.71
42
- silence_before_correction: -0.02
43
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
44
- non_silence_before_correction: -0.01
45
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
46
- probability: 0.34
47
  replacement: ''
48
  segment: ɯ
49
- silence_after_probability: 0.57
50
- silence_before_correction: 0.07
51
  - following_context: $
52
  non_silence_before_correction: 0.08
53
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
54
- probability: 0.06
55
  replacement: ɯ̥
56
  segment: ɯ
57
- silence_after_probability: 0.13
58
- silence_before_correction: -0.31
59
  - following_context: $
60
- non_silence_before_correction: 0.08
61
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
62
- probability: 0.03
63
  replacement: ''
64
  segment: ɯ
65
- silence_after_probability: 1.0
66
- silence_before_correction: -0.35
67
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
68
- non_silence_before_correction: -0.02
69
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
70
- probability: 0.09
71
  replacement: ɨ̥
72
  segment: ɨ
73
- silence_after_probability: 0.94
74
- silence_before_correction: 0.03
75
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
76
- non_silence_before_correction: -0.01
77
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
78
- probability: 0.42
79
  replacement: ''
80
  segment: ɨ
81
- silence_after_probability: 0.89
82
- silence_before_correction: 0.04
83
  - following_context: $
84
- non_silence_before_correction: 0.02
85
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
86
- probability: 0.06
87
  replacement: ɨ̥
88
  segment: ɨ
89
- silence_after_probability: 5.0
90
- silence_before_correction: -0.13
91
  - following_context: $
92
- non_silence_before_correction: 0.05
93
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
94
- probability: 0.05
95
  replacement: ''
96
  segment: ɨ
97
- silence_after_probability: 5.8
98
- silence_before_correction: -0.21
99
  rules: []
 
1
  dialects:
2
  us:
3
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
4
+ non_silence_before_correction: 0.12
5
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
6
+ probability: 0.01
7
  replacement: i̥
8
  segment: i
9
+ silence_after_probability: 0.22
10
+ silence_before_correction: -0.36
11
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
12
+ non_silence_before_correction: 0.11
13
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
14
+ probability: 0.01
15
  replacement: ''
16
  segment: i
17
+ silence_after_probability: 0.29
18
+ silence_before_correction: -0.33
19
  - following_context: $
20
+ non_silence_before_correction: 0.07
21
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
22
+ probability: 0.01
23
  replacement: i̥
24
  segment: i
25
+ silence_after_probability: 0.01
26
+ silence_before_correction: -0.22
27
  - following_context: $
28
+ non_silence_before_correction: 0.08
29
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
30
+ probability: 0.01
31
  replacement: ''
32
  segment: i
33
+ silence_after_probability: 0.12
34
+ silence_before_correction: -0.29
35
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
36
+ non_silence_before_correction: 0.08
37
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
38
+ probability: 0.01
39
  replacement: ɯ̥
40
  segment: ɯ
41
+ silence_after_probability: 0.18
42
+ silence_before_correction: -0.27
43
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
44
+ non_silence_before_correction: 0.07
45
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
46
+ probability: 0.01
47
  replacement: ''
48
  segment: ɯ
49
+ silence_after_probability: 0.13
50
+ silence_before_correction: -0.17
51
  - following_context: $
52
  non_silence_before_correction: 0.08
53
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
54
+ probability: 0.01
55
  replacement: ɯ̥
56
  segment: ɯ
57
+ silence_after_probability: 0.03
58
+ silence_before_correction: -0.24
59
  - following_context: $
60
+ non_silence_before_correction: 0.1
61
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
62
+ probability: 0.01
63
  replacement: ''
64
  segment: ɯ
65
+ silence_after_probability: 0.2
66
+ silence_before_correction: -0.34
67
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
68
+ non_silence_before_correction: 0.09
69
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
70
+ probability: 0.01
71
  replacement: ɨ̥
72
  segment: ɨ
73
+ silence_after_probability: 0.21
74
+ silence_before_correction: -0.32
75
  - following_context: '[skctɕɸçhp][ʲsɕ]?ː?'
76
+ non_silence_before_correction: 0.1
77
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
78
+ probability: 0.01
79
  replacement: ''
80
  segment: ɨ
81
+ silence_after_probability: 0.25
82
+ silence_before_correction: -0.26
83
  - following_context: $
84
+ non_silence_before_correction: 0.05
85
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
86
+ probability: 0.01
87
  replacement: ɨ̥
88
  segment: ɨ
89
+ silence_after_probability: 0.41
90
+ silence_before_correction: -0.17
91
  - following_context: $
92
+ non_silence_before_correction: 0.11
93
  preceding_context: '[skctɕɸçhp][ʲsɕ]?ː?'
94
+ probability: 0.01
95
  replacement: ''
96
  segment: ɨ
97
+ silence_after_probability: 0.45
98
+ silence_before_correction: -0.35
99
  rules: []
g2p/japanese_katakana_mfa/graphemes.sym ADDED
@@ -0,0 +1,1194 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <eps> 0
2
+ | 1
3
+ _ 2
4
+ あ 3
5
+ ぁ 4
6
+ あ|い 5
7
+ う 6
8
+ ふ|う 7
9
+ に 8
10
+ え 9
11
+ ば 10
12
+ こ|う 11
13
+ い|う 12
14
+ っ|た 13
15
+ し 14
16
+ た 15
17
+ て 16
18
+ ろ 17
19
+ だ 18
20
+ で 19
21
+ も 20
22
+ な 21
23
+ い 22
24
+ と 23
25
+ み 24
26
+ あ|や 25
27
+ っ|て 26
28
+ ゆ|う 27
29
+ ん 28
30
+ か 29
31
+ ご 30
32
+ が 31
33
+ さ 32
34
+ し|い 33
35
+ あ|う 34
36
+ わ 35
37
+ れ 36
38
+ む 37
39
+ い|い 38
40
+ く 39
41
+ せ|い 40
42
+ す 41
43
+ ず 42
44
+ ら 43
45
+ ろ|う 44
46
+ け 45
47
+ よ 46
48
+ よ|う 47
49
+ る 48
50
+ き 49
51
+ し|ゃ 50
52
+ お 51
53
+ じ|ゅ 52
54
+ ひ 53
55
+ ょ|う 54
56
+ ち 55
57
+ つ 56
58
+ え|ん 57
59
+ ん|き 58
60
+ お|い 59
61
+ の 60
62
+ ま 61
63
+ び 62
64
+ ぎ 63
65
+ お|ん 64
66
+ ど 65
67
+ り 66
68
+ け|い 67
69
+ こ 68
70
+ カ 69
71
+ レ|ー 70
72
+ め 71
73
+ ぶ 72
74
+ ど|う 73
75
+ き|ゃ 74
76
+ ゅ|う 75
77
+ げ 76
78
+ っ|ぷ 77
79
+ づ 78
80
+ ち|い 79
81
+ べ 80
82
+ ぼ 81
83
+ を 82
84
+ ふ 83
85
+ ぎ|ょ 84
86
+ お|う 85
87
+ や 86
88
+ ぐ 87
89
+ う|ん 88
90
+ し|ゅ 89
91
+ っ|か 90
92
+ ご|う 91
93
+ と|う 92
94
+ せ 93
95
+ は 94
96
+ の|う 95
97
+ じ 96
98
+ ぬ 97
99
+ ざ 98
100
+ い|し 99
101
+ し|ょ 100
102
+ き|ょ 101
103
+ じ|ゃ 102
104
+ い|じ 103
105
+ っ|す 104
106
+ ぜ 105
107
+ ぜ|ん 106
108
+ そ 107
109
+ そ|う 108
110
+ を|ふ 109
111
+ ぞ|う 110
112
+ へ|い 111
113
+ ぞ 112
114
+ ん|じ 113
115
+ た|っ 114
116
+ っ|と 115
117
+ を|あ 116
118
+ を|お 117
119
+ ち|ゃ 118
120
+ つ|う 119
121
+ を|う 120
122
+ て|い 121
123
+ ね 122
124
+ っ|し 123
125
+ を|い 124
126
+ も|う 125
127
+ ぼ|う 126
128
+ ぢ 127
129
+ ゃ 128
130
+ い|り 129
131
+ ア 130
132
+ ク 131
133
+ セ 132
134
+ ン 133
135
+ ト 134
136
+ を|ぬ 135
137
+ ょ 136
138
+ め|い 137
139
+ ん|の 138
140
+ あ|え 139
141
+ え|い 140
142
+ ん|ち 141
143
+ っ|ぱ 142
144
+ メ 143
145
+ ッ|キ 144
146
+ あ|お 145
147
+ は|っ 146
148
+ ダ 147
149
+ イ 148
150
+ オ|ー 149
151
+ ド 150
152
+ お|お 151
153
+ ん|な 152
154
+ ぴ 153
155
+ ん|し 154
156
+ げ|い 155
157
+ イ|ン 156
158
+ テ 157
159
+ リ 158
160
+ っ|ぽ 159
161
+ り|い 160
162
+ は|ん 161
163
+ ゆ 162
164
+ く|う 163
165
+ ビ 164
166
+ ジ 165
167
+ ソ 166
168
+ タ 167
169
+ ナ 168
170
+ バ|ー 169
171
+ ほ|う 170
172
+ ほ|お 171
173
+ り|ょ 172
174
+ げ|ん 173
175
+ ノ 174
176
+ ス 175
177
+ か|れ 176
178
+ れ|い 177
179
+ き|い 178
180
+ ワ 179
181
+ ラ 180
182
+ ビ|ー 181
183
+ っ|こ 182
184
+ を|ひ 183
185
+ ポ 184
186
+ っ 185
187
+ ね|い 186
188
+ へ 187
189
+ ほ 188
190
+ ぽ 189
191
+ か|ん 190
192
+ べ|い 191
193
+ ー 192
194
+ ゲ|ン 193
195
+ ウ|ィ 194
196
+ ナ|ー 195
197
+ ウ 196
198
+ エ|イ 197
199
+ ブ 198
200
+ ガ 199
201
+ ル|ー 200
202
+ キ|ャ 201
203
+ ベ 202
204
+ ツ 203
205
+ ゲ 204
206
+ ッ|ト 205
207
+ グ 206
208
+ チ 207
209
+ パ 208
210
+ ド|ウ 209
211
+ プ 210
212
+ マ 211
213
+ グ|ー 212
214
+ ム 213
215
+ レ 214
216
+ ハ 215
217
+ の|お 216
218
+ う|ぎ 217
219
+ と|お 218
220
+ っ|き 219
221
+ フ|ァ 220
222
+ ル 221
223
+ ぎ|ゃ 222
224
+ ざ|ん 223
225
+ ぜ|い 224
226
+ と|を 225
227
+ ひ|ゃ 226
228
+ じ|ょ 227
229
+ せ|ん 228
230
+ コ 229
231
+ ロ|ー 230
232
+ サ 231
233
+ す|う 232
234
+ ぐ|う 233
235
+ っ|ぴ 234
236
+ ギ|ョ 235
237
+ ー|ザ 236
238
+ ヒ 237
239
+ バ 238
240
+ を|だ 239
241
+ ひ|い 240
242
+ い|て 241
243
+ さ|ん 242
244
+ ば|ん 243
245
+ ぎ|い 244
246
+ っ|そ 245
247
+ シ|ャ 246
248
+ チ|ュ 247
249
+ も|お 248
250
+ に|ょ 249
251
+ ミ 250
252
+ ア|ン 251
253
+ モ 252
254
+ ニ 253
255
+ み|い 254
256
+ キ 255
257
+ っ|け 256
258
+ ッ|ク 257
259
+ ぱ 258
260
+ フ 259
261
+ ア|イ 260
262
+ コ|ー 261
263
+ ど|っ 262
264
+ に|い 263
265
+ た|た 264
266
+ へ|ん 265
267
+ ネ 266
268
+ ズ 267
269
+ ペ|ー 268
270
+ し|ん 269
271
+ ラ|ッ 270
272
+ カ|ー 271
273
+ ぃ 272
274
+ あ|っ 273
275
+ っ|く 274
276
+ っ|さ 275
277
+ ア|ー 276
278
+ オ 277
279
+ モ|ー 278
280
+ っ|せ 279
281
+ ん|い 280
282
+ ん|ぎ 281
283
+ ん|り 282
284
+ っ|ち 283
285
+ ち|ゅ 284
286
+ ベ|ー 285
287
+ プ|ー 286
288
+ ぽ|う 287
289
+ ジ|ャ 288
290
+ ケ 289
291
+ ピ 290
292
+ チ|ー 291
293
+ ん|に 292
294
+ ジ|ェ 293
295
+ み|ゃ 294
296
+ ね|え 295
297
+ ギ|ッ 296
298
+ シ|ュ 297
299
+ ペ|イ 298
300
+ ぷ 299
301
+ を|す 300
302
+ ダ|ー 301
303
+ お|ち 302
304
+ ま|っ 303
305
+ ち|ょ 304
306
+ な|っ 305
307
+ ッ|パ 306
308
+ ロ 307
309
+ い|ち 308
310
+ を|も 309
311
+ ゴ 310
312
+ ワ|ー 311
313
+ マ|ー 312
314
+ ウ|ェ 313
315
+ べ|ん 314
316
+ ら|あ 315
317
+ あ|ら 316
318
+ ソ|ー 317
319
+ セ|ー 318
320
+ あ|ん 319
321
+ ぃ|ー 320
322
+ り|っ 321
323
+ ど|お 322
324
+ り|ゃ 323
325
+ で|は 324
326
+ リ|ー 325
327
+ か|っ 326
328
+ エ 327
329
+ ギ|ー 328
330
+ シ 329
331
+ キ|ー 330
332
+ メ|ー 331
333
+ ゅ|ん 332
334
+ せ|っ 333
335
+ サ|ー 334
336
+ タ|ー 335
337
+ ッ|チ 336
338
+ オ|ン 337
339
+ ッ 338
340
+ リ|ャ 339
341
+ ・ 340
342
+ い|え 341
343
+ い|っ 342
344
+ っ|ぺ 343
345
+ ぼ|っ 344
346
+ を|え 345
347
+ ぇ 346
348
+ ぇ|い 347
349
+ え|を 348
350
+ デ 349
351
+ く|る 350
352
+ が|ん 351
353
+ て|ん 352
354
+ い|き 353
355
+ じ|い 354
356
+ ゼ 355
357
+ に|ん 356
358
+ ね|ん 357
359
+ ず|う 358
360
+ チ|ャ 359
361
+ ペ 360
362
+ ご|っ 361
363
+ ご|ん 362
364
+ ザ 363
365
+ け|っ 364
366
+ か|く 365
367
+ デ|ィ 366
368
+ ネ|ー 367
369
+ セ|ル 368
370
+ ゲ|ー 369
371
+ お|や 370
372
+ ッ|プ 371
373
+ じ|ん 372
374
+ ぞ|ん 373
375
+ ろ|を 374
376
+ ん|で 375
377
+ ぎ|ん 376
378
+ チ|ョ 377
379
+ ネ|イ 378
380
+ ッ|グ 379
381
+ ざ|っ 380
382
+ う|ち 381
383
+ フ|ェ 382
384
+ ー|ス 383
385
+ ラ|ー 384
386
+ っ|つ 385
387
+ ご|お 386
388
+ き|ん 387
389
+ も|ん 388
390
+ お|し 389
391
+ リ|ッ 390
392
+ け|ん 391
393
+ ビ|ッ 392
394
+ ら|っ 393
395
+ を|た 394
396
+ ギ|ャ 395
397
+ と|っ 396
398
+ デ|ー 397
399
+ ピ|ー 398
400
+ ポ|ー 399
401
+ ユ|ー 400
402
+ ザ|ー 401
403
+ オ|オ 402
404
+ ぷ|う 403
405
+ ぺ|い 404
406
+ で|い 405
407
+ ゲ|ッ 406
408
+ テ|ィ 407
409
+ で|ん 408
410
+ こ|ん 409
411
+ に|ゃ 410
412
+ コ|ン 411
413
+ ニ|ャ 412
414
+ た|ん 413
415
+ い|に 414
416
+ パ|ー 415
417
+ ゾ 416
418
+ い|ひ 417
419
+ び|い 418
420
+ び|ゃ 419
421
+ フ|ィ 420
422
+ ウ|ン 421
423
+ み|ん 422
424
+ う|と 423
425
+ い|も 424
426
+ い|や 425
427
+ う|も 426
428
+ ま|ん 427
429
+ い|ん 428
430
+ い|ろ 429
431
+ ろ|お 430
432
+ テ|ー 431
433
+ ギ 432
434
+ ふ|る 433
435
+ も|っ 434
436
+ ュ|ー 435
437
+ ホ 436
438
+ イ|ー 437
439
+ ポ|リ 438
440
+ ー|プ 439
441
+ ぺ 440
442
+ ぅ 441
443
+ ぅ|ー 442
444
+ う|め 443
445
+ お|さ 444
446
+ ぉ 445
447
+ ��|お 446
448
+ こ|っ 447
449
+ う|じ 448
450
+ ぴ|ゃ 449
451
+ ぴ|ょ 450
452
+ を|つ 451
453
+ が|っ 452
454
+ ば|っ 453
455
+ ん|え 454
456
+ シ|ョ 455
457
+ や|ん 456
458
+ う|て 457
459
+ ひ|し 458
460
+ う|ふ 459
461
+ ま|い 460
462
+ や|っ 461
463
+ エ|ン 462
464
+ ッ|サ 463
465
+ ー|ブ 464
466
+ ボ 465
467
+ だ|か 466
468
+ る|お 467
469
+ る|さ 468
470
+ さ|い 469
471
+ う|わ 470
472
+ ぁ|ー 471
473
+ ・|ス 472
474
+ ヌ 473
475
+ エ|ー 474
476
+ め|ん 475
477
+ ひ|ん 476
478
+ さ|っ 477
479
+ ト|ン 478
480
+ ふ|り 479
481
+ ヘ 480
482
+ え|か 481
483
+ え|っ 482
484
+ え|ま 483
485
+ な|い 484
486
+ レ|イ 485
487
+ シ|ー 486
488
+ ま|え 487
489
+ え|せ 488
490
+ ス|ー 489
491
+ え|れ 490
492
+ ジ|ョ 491
493
+ ユ 492
494
+ ト|ー 493
495
+ ド|ル 494
496
+ け|れ 495
497
+ ら|ん 496
498
+ だ|ん 497
499
+ ッ|セ 498
500
+ ー|ジ 499
501
+ ぶ|ん 500
502
+ フ|ォ 501
503
+ み|う 502
504
+ ッ|ケ 503
505
+ お|ま 504
506
+ イ|チ 505
507
+ ョ|ウ 506
508
+ ほ|っ 507
509
+ ケ|ー 508
510
+ デ|ュ 509
511
+ お|そ 510
512
+ お|っ 511
513
+ を|し 512
514
+ を|み 513
515
+ ぁ|ん 514
516
+ お|な 515
517
+ ば|あ 516
518
+ に|ゅ 517
519
+ を|と 518
520
+ す|る 519
521
+ お|め 520
522
+ れ|っ 521
523
+ お|も 522
524
+ グ|ッ 523
525
+ ニ|ュ 524
526
+ ピ|ア 525
527
+ つ|え 526
528
+ ー|ル 527
529
+ ー|マ 528
530
+ メ|イ 529
531
+ げ|っ 530
532
+ に|っ 531
533
+ ホ|ー 532
534
+ じ|っ 533
535
+ ツ|ー 534
536
+ ッ|ド 535
537
+ な|ん 536
538
+ お|す 537
539
+ か|お 538
540
+ を|か 539
541
+ を|き 540
542
+ を|そ 541
543
+ を|な 542
544
+ を|の 543
545
+ を|ゆ 544
546
+ ボ|ー 545
547
+ ッ|コ 546
548
+ ェ 547
549
+ べ|っ 548
550
+ セ|ン 549
551
+ て|っ 550
552
+ ぐ|ん 551
553
+ ぶ|っ 552
554
+ で|っ 553
555
+ ヤ 554
556
+ ラ|ン 555
557
+ れ|な 556
558
+ し|っ 557
559
+ エ|ア 558
560
+ を|ま 559
561
+ わ|っ 560
562
+ ー|エ 561
563
+ ん|さ 562
564
+ そ|ん 563
565
+ そ|っ 564
566
+ ヒ|ー 565
567
+ オ|ウ 566
568
+ ヨ|ウ 567
569
+ が|あ 568
570
+ き|お 569
571
+ ブ|ー 570
572
+ ほ|ん 571
573
+ ふ|っ 572
574
+ チ|ェ 573
575
+ ウ|ォ 574
576
+ ヨ|ー 575
577
+ き|っ 576
578
+ ー|ド 577
579
+ ジ|ー 578
580
+ き|ゅ 579
581
+ ェ|ー 580
582
+ バ|ッ 581
583
+ ぜ|っ 582
584
+ お|く 583
585
+ を|さ 584
586
+ び|お 585
587
+ ッ|カ 586
588
+ ボ|ウ 587
589
+ れ|ん 588
590
+ ッ|ジ 589
591
+ ぎ|っ 590
592
+ フ|ー 591
593
+ ャ|ー 592
594
+ ッ|ピ 593
595
+ ぎ|ゅ 594
596
+ ィ 595
597
+ ア|ウ 596
598
+ ハ|ン 597
599
+ く|せ 598
600
+ お|け 599
601
+ お|と 600
602
+ を|く 601
603
+ だ|っ 602
604
+ を|む 603
605
+ ゑ 604
606
+ ゎ 605
607
+ う|し 606
608
+ ん|が 607
609
+ ん|て 608
610
+ ド|ー 609
611
+ な|か 610
612
+ マ|ン 611
613
+ ジ|ン 612
614
+ ー|ム 613
615
+ ぷ|ん 614
616
+ プ|ン 615
617
+ セ|ッ 616
618
+ を|こ 617
619
+ ス|ウ 618
620
+ ゾ|ー 619
621
+ リ|ン 620
622
+ ブ|ッ 621
623
+ ポ|ウ 622
624
+ ソ|ウ 623
625
+ あ|げ 624
626
+ ニ|ー 625
627
+ ぁ|な 626
628
+ ヨ 627
629
+ う|ご 628
630
+ う|た 629
631
+ う|つ 630
632
+ う|ば 631
633
+ ミ|ュ 632
634
+ ぢ|ん 633
635
+ を|は 634
636
+ ぼ|ん 635
637
+ を|や 636
638
+ ウ|マ 637
639
+ あ|さ 638
640
+ う|り 639
641
+ ろ|っ 640
642
+ ケ|イ 641
643
+ ェ|ア 642
644
+ め|っ 643
645
+ ゥ 644
646
+ レ|ン 645
647
+ ー|ト 646
648
+ ノ|ー 647
649
+ か|い 648
650
+ ひ|っ 649
651
+ い|な 650
652
+ り|ん 651
653
+ ゴ|ー 652
654
+ う|ま 653
655
+ ウ|イ 654
656
+ ベ|イ 655
657
+ オ|リ 656
658
+ ヱ 657
659
+ ュ|ウ 658
660
+ ッ|シ 659
661
+ ギ|ュ 660
662
+ ね|っ 661
663
+ ョ|ン 662
664
+ イ|ウ 663
665
+ ェ|イ 664
666
+ キ|ュ 665
667
+ べ|え 666
668
+ ふ|ん 667
669
+ ご|い 668
670
+ す|っ 669
671
+ ん|げ 670
672
+ す|ん 671
673
+ ず|っ 672
674
+ ッ|タ 673
675
+ め|を 674
676
+ ん|ご 675
677
+ ガ|ー 676
678
+ ゅ 677
679
+ ん|ど 678
680
+ と|ん 679
681
+ お|き 680
682
+ お|ど 681
683
+ ぞ|っ 682
684
+ ロ|ッ 683
685
+ を|よ 684
686
+ ガ|ン 685
687
+ オ|イ 686
688
+ ヴ|ァ 687
689
+ ミ|ー 688
690
+ テ|ン 689
691
+ ハ|ー 690
692
+ み|っ 691
693
+ ち|っ 692
694
+ ホ|ウ 693
695
+ カ|ン 694
696
+ わ|ん 695
697
+ ち|ん 696
698
+ ジ|ュ 697
699
+ ぢ|ゃ 698
700
+ ぢ|ょ 699
701
+ ッ|ポ 700
702
+ ま|げ 701
703
+ ヲ 702
704
+ ヤ|ー 703
705
+ で|す 704
706
+ ハ|ッ 705
707
+ ア|ラ 706
708
+ び|ん 707
709
+ し|の 708
710
+ ど|ん 709
711
+ ん|せ 710
712
+ あ|な 711
713
+ ロ|ウ 712
714
+ ッ|ス 713
715
+ ぞ|を 714
716
+ ダ|ッ 715
717
+ よ|っ 716
718
+ に|お 717
719
+ ひ|ょ 718
720
+ の|っ 719
721
+ ッ|テ 720
722
+ は|い 721
723
+ イ|リ 722
724
+ つ|ま 723
725
+ ゼ|ー 724
726
+ ジ|ッ 725
727
+ た|い 726
728
+ イ|オ 727
729
+ ヅ 728
730
+ パ|ン 729
731
+ う|ら 730
732
+ び|っ 731
733
+ も|の 732
734
+ み|ょ 733
735
+ び|ゅ 734
736
+ ま|り 735
737
+ う|ぶ 736
738
+ ぶ|る 737
739
+ ぇ|ー 738
740
+ へ|っ 739
741
+ お|び 740
742
+ マ|ッ 741
743
+ ぽ|っ 742
744
+ ま|あ 743
745
+ を|わ 744
746
+ ん|そ 745
747
+ ん|ぽ 746
748
+ ダ|ン 747
749
+ お|せ 748
750
+ ば|い 749
751
+ う|け 750
752
+ タ|ッ 751
753
+ を|て 752
754
+ よ|ん 753
755
+ り|を 754
756
+ デ|イ 755
757
+ と|も 756
758
+ ぬ|り 757
759
+ フ|ッ 758
760
+ ろ|ん 759
761
+ あ|わ 760
762
+ ゐ 761
763
+ ァ 762
764
+ コ|ウ 763
765
+ ア|ヤ 764
766
+ ユ|ウ 765
767
+ ン|・ 766
768
+ ・|サ 767
769
+ イ|イ 768
770
+ セ|イ 769
771
+ ン|キ 770
772
+ チ|イ 771
773
+ シ|イ 772
774
+ ・|エ 773
775
+ ゴ|ウ 774
776
+ イ|シ 775
777
+ キ|ョ 776
778
+ グ|・ 777
779
+ ・|パ 778
780
+ イ|ジ 779
781
+ ツ|ウ 780
782
+ ム|・ 781
783
+ ホ|ッ 782
784
+ ン|リ 783
785
+ ス|・ 784
786
+ ・|プ 785
787
+ ゼ|ン 786
788
+ ・|ポ 787
789
+ ヲ|ツ 788
790
+ ヲ|フ 789
791
+ ゾ|ウ 790
792
+ ヘ|イ 791
793
+ ン|ジ 792
794
+ ヲ|ア 793
795
+ ヲ|オ 794
796
+ ト|ウ 795
797
+ テ|イ 796
798
+ ノ|ウ 797
799
+ ア|・ 798
800
+ ー|ク 799
801
+ ー|・ 800
802
+ ル|・ 801
803
+ ヲ|ウ 802
804
+ モ|ウ 803
805
+ シ|ェ 804
806
+ ・|ペ 805
807
+ ・|ブ 806
808
+ イ|ヒ 807
809
+ ヂ 808
810
+ ャ 809
811
+ ヲ|ヌ 810
812
+ ド|・ 811
813
+ ・|ウ 812
814
+ ウ|チ 813
815
+ ヴ|ォ 814
816
+ ・|ア 815
817
+ ・|オ 816
818
+ ヌ|・ 817
819
+ ・|コ 818
820
+ ・|シ 819
821
+ ・|バ 820
822
+ ・|ピ 821
823
+ ・|マ 822
824
+ ・|ラ 823
825
+ ブ|・ 824
826
+ ッ|ツ 825
827
+ ヴ|ィ 826
828
+ ウ|ト 827
829
+ ト|ゥ 828
830
+ ワ|ッ 829
831
+ ト|オ 830
832
+ ン|チ 831
833
+ ・|レ 832
834
+ ・|ボ 833
835
+ ト|・ 834
836
+ ン|シ 835
837
+ エ|ク 836
838
+ ェ|ン 837
839
+ ア|オ 838
840
+ ゲ|イ 839
841
+ キ|イ 840
842
+ リ|イ 841
843
+ ク|ウ 842
844
+ ホ|オ 843
845
+ リ|ョ 844
846
+ フ|ウ 845
847
+ ヲ|ヒ 846
848
+ ミ|ン 847
849
+ ・|ハ 848
850
+ ゼ|イ 849
851
+ ォ 850
852
+ ザ|ン 851
853
+ ヒ|ャ 852
854
+ ネ|ン 853
855
+ ン|ス 854
856
+ サ|ン 855
857
+ ヴ 856
858
+ カ|レ 857
859
+ ・|ダ 858
860
+ レ|ッ 859
861
+ ア|ケ 860
862
+ ア|ゲ 861
863
+ ィ|ン 862
864
+ ー|ン 863
865
+ ・|ド 864
866
+ ヲ|ダ 865
867
+ ヒ|イ 866
868
+ モ|ン 867
869
+ バ|ン 868
870
+ ギ|イ 869
871
+ ッ|ソ 870
872
+ ヲ|ノ 871
873
+ ヲ|コ 872
874
+ ヲ|シ 873
875
+ ヲ|タ 874
876
+ ン|ト 875
877
+ ノ|オ 876
878
+ オ|ヨ 877
879
+ ヲ|ス 878
880
+ ヲ|ミ 879
881
+ ニ|ョ 880
882
+ ミ|イ 881
883
+ シ|ン 882
884
+ ・|デ 883
885
+ ・|ビ 884
886
+ イ|ス 885
887
+ ソ|ン 886
888
+ ブ|ン 887
889
+ ニ|ッ 888
890
+ ヲ|イ 889
891
+ ニ|イ 890
892
+ タ|タ 891
893
+ ヘ|ン 892
894
+ エ|モ 893
895
+ ア|ッ 894
896
+ ・|メ 895
897
+ ズ|・ 896
898
+ ォ|ー 897
899
+ ・|ク 898
900
+ ミ|ャ 899
901
+ ア|ト 900
902
+ ヲ|ト 901
903
+ ア|ド 902
904
+ ド|ゥ 903
905
+ ド|オ 904
906
+ ッ|フ 905
907
+ ・|フ 906
908
+ ヴ|ェ 907
909
+ ・|ソ 908
910
+ パ|ッ 909
911
+ ・|グ 910
912
+ ー|チ 911
913
+ ー|ア 912
914
+ ー|ダ 913
915
+ ナ|イ 914
916
+ ヌ|ー 915
917
+ ュ 916
918
+ チ|・ 917
919
+ ジ|・ 918
920
+ レ|オ 919
921
+ ナ|ッ 920
922
+ ヲ|モ 921
923
+ ー|ズ 922
924
+ ア|ミ 923
925
+ ベ|ン 924
926
+ デ|ハ 925
927
+ ド|ン 926
928
+ キ|ン 927
929
+ ペ|ッ 928
930
+ ・|セ 929
931
+ ・|ホ 930
932
+ ・|モ 931
933
+ ・|テ 932
934
+ ・|ベ 933
935
+ カ|ッ 934
936
+ グ|ウ 935
937
+ ュ|ン 936
938
+ ク|・ 937
939
+ ザ|・ 938
940
+ ・|リ 939
941
+ ン|ド 940
942
+ ゥ|ー 941
943
+ ビ|ュ 942
944
+ ボ|ン 943
945
+ ピ|ュ 944
946
+ ミ|ッ 945
947
+ オ|・ 946
948
+ ヨ|ン 947
949
+ リ|ュ 948
950
+ フ|・ 949
951
+ イ|エ 950
952
+ イ|ッ 951
953
+ シ|ッ 952
954
+ ボ|ッ 953
955
+ ヲ|エ 954
956
+ ヲ|カ 955
957
+ ウ|モ 956
958
+ ・|ジ 957
959
+ ・|タ 958
960
+ エ|ヲ 959
961
+ オ|ッ 960
962
+ ャ|ン 961
963
+ コ|オ 962
964
+ フ|ル 963
965
+ イ|キ 964
966
+ ニ|ン 965
967
+ ズ|ウ 966
968
+ ゴ|ン 967
969
+ ケ|ッ 968
970
+ カ|ク 969
971
+ ケ|ン 970
972
+ ゾ|ン 971
973
+ ロ|ヲ 972
974
+ ン|デ 973
975
+ ギ|ン 974
976
+ ザ|ッ 975
977
+ ン|ゴ 976
978
+ タ|ン 977
979
+ ナ|ン 978
980
+ ト|ッ 979
981
+ プ|ウ 980
982
+ ペ|ン 981
983
+ イ|テ 982
984
+ デ|ン 983
985
+ ヲ|ハ 984
986
+ イ|ニ 985
987
+ ビ|イ 986
988
+ ビ|ャ 987
989
+ ・|イ 988
990
+ イ|ヤ 989
991
+ ヤ|ッ 990
992
+ イ|ロ 991
993
+ ロ|ン 992
994
+ コ|ッ 993
995
+ モ|ッ 994
996
+ ヴ|ュ 995
997
+ ネ|ッ 996
998
+ ・|ロ 997
999
+ ィ|ア 998
1000
+ ・|ト 999
1001
+ ト|リ 1000
1002
+ ィ|ー 1001
1003
+ ウ|ム 1002
1004
+ ウ|メ 1003
1005
+ イ|ク 1004
1006
+ イ|ズ 1005
1007
+ ァ|ー 1006
1008
+ イ|ブ 1007
1009
+ イ|ボ 1008
1010
+ イ|ラ 1009
1011
+ イ|ル 1010
1012
+ ー|デ 1011
1013
+ オ|サ 1012
1014
+ ー|ニ 1013
1015
+ ウ|ジ 1014
1016
+ ピ|ャ 1015
1017
+ ウ|ソ 1016
1018
+ ガ|ッ 1017
1019
+ オ|マ 1018
1020
+ ウ|テ 1019
1021
+ ヒ|シ 1020
1022
+ マ|イ 1021
1023
+ ダ|カ 1022
1024
+ ウ|ル 1023
1025
+ サ|イ 1024
1026
+ ウ|ロ 1025
1027
+ メ|ン 1026
1028
+ ヒ|ン 1027
1029
+ サ|ッ 1028
1030
+ フ|リ 1029
1031
+ エ|ッ 1030
1032
+ エ|ト 1031
1033
+ マ|エ 1032
1034
+ ・|ネ 1033
1035
+ プ|・ 1034
1036
+ キ|ッ 1035
1037
+ ド|ッ 1036
1038
+ ワ|ン 1037
1039
+ エ|レ 1038
1040
+ エ|ロ 1039
1041
+ ケ|レ 1040
1042
+ テ|ッ 1041
1043
+ ミ|ウ 1042
1044
+ コ|テ 1043
1045
+ エ|ネ 1044
1046
+ オ|ソ 1045
1047
+ デ|ッ 1046
1048
+ ァ|ン 1047
1049
+ オ|ナ 1048
1050
+ ヤ|ン 1049
1051
+ ス|ル 1050
1052
+ オ|ブ 1051
1053
+ メ|ニ 1052
1054
+ オ|メ 1053
1055
+ オ|モ 1054
1056
+ オ|ラ 1055
1057
+ ツ|エ 1056
1058
+ オ|ロ 1057
1059
+ チ|ッ 1058
1060
+ バ|レ 1059
1061
+ イ|ト 1060
1062
+ ・|ミ 1061
1063
+ ン|グ 1062
1064
+ ヲ|キ 1063
1065
+ ヲ|ソ 1064
1066
+ ヲ|ナ 1065
1067
+ ヲ|ユ 1066
1068
+ ベ|ッ 1067
1069
+ フ|ン 1068
1070
+ ー|キ 1069
1071
+ ミ|オ 1070
1072
+ ウ|コ 1071
1073
+ レ|ナ 1072
1074
+ ハ|イ 1073
1075
+ ワ|イ 1074
1076
+ ヲ|マ 1075
1077
+ ン|サ 1076
1078
+ な|べ 1077
1079
+ ・|ゲ 1078
1080
+ ガ|ア 1079
1081
+ ピ|ン 1080
1082
+ ネ|ジ 1081
1083
+ プ|ッ 1082
1084
+ キ|オ 1083
1085
+ オ|ス 1084
1086
+ ホ|ン 1085
1087
+ チ|ン 1086
1088
+ ゼ|ッ 1087
1089
+ オ|ク 1088
1090
+ カ|イ 1089
1091
+ ヲ|サ 1090
1092
+ ビ|オ 1091
1093
+ ァ|イ 1092
1094
+ ・|チ 1093
1095
+ メ|ッ 1094
1096
+ ク|セ 1095
1097
+ オ|ケ 1096
1098
+ オ|チ 1097
1099
+ オ|ト 1098
1100
+ ヲ|ム 1099
1101
+ ヴ|・ 1100
1102
+ ー|ナ 1101
1103
+ ー|フ 1102
1104
+ ヮ|ー 1103
1105
+ グ|ン 1104
1106
+ ナ|カ 1105
1107
+ イ|ド 1106
1108
+ イ|デ 1107
1109
+ ウ|ゴ 1108
1110
+ ウ|タ 1109
1111
+ ウ|バ 1110
1112
+ ヂ|ン 1111
1113
+ シ|サ 1112
1114
+ ヲ|ワ 1113
1115
+ ヲ|ヤ 1114
1116
+ ピ|ッ 1115
1117
+ オ|ヤ 1116
1118
+ ポ|ッ 1117
1119
+ ア|サ 1118
1120
+ イ|ケ 1119
1121
+ ツ|オ 1120
1122
+ ヘ|ッ 1121
1123
+ ズ|ン 1122
1124
+ ク|ロ 1123
1125
+ オ|ワ 1124
1126
+ ヮ 1125
1127
+ ノ|ン 1126
1128
+ ウ|ツ 1127
1129
+ ヒ|ッ 1128
1130
+ イ|ナ 1129
1131
+ ウ|ミ 1130
1132
+ イ|ダ 1131
1133
+ エ|ズ 1132
1134
+ ゴ|イ 1133
1135
+ ノ|ッ 1134
1136
+ マ|ゲ 1135
1137
+ ズ|ッ 1136
1138
+ メ|ヲ 1137
1139
+ オ|ド 1138
1140
+ ソ|コ 1139
1141
+ ソ|ッ 1140
1142
+ ヲ|ニ 1141
1143
+ ゾ|ッ 1142
1144
+ ウ|ス 1143
1145
+ ヲ|ヨ 1144
1146
+ ン|テ 1145
1147
+ ォ|ン 1146
1148
+ ポ|ン 1147
1149
+ ヂ|ョ 1148
1150
+ ィ|ッ 1149
1151
+ ェ|ッ 1150
1152
+ い|た 1151
1153
+ オ|ノ 1152
1154
+ ョ 1153
1155
+ ロ|ミ 1154
1156
+ デ|ス 1155
1157
+ ラ|イ 1156
1158
+ ビ|ン 1157
1159
+ シ|ノ 1158
1160
+ ア|ナ 1159
1161
+ デ|オ 1160
1162
+ ヒ|ョ 1161
1163
+ ツ|マ 1162
1164
+ ニ|ジ 1163
1165
+ ク|イ 1164
1166
+ ポ|ケ 1165
1167
+ ヒ|ュ 1166
1168
+ ニ|テ 1167
1169
+ マ|リ 1168
1170
+ モ|ノ 1169
1171
+ ミ|ョ 1170
1172
+ ヌ|エ 1171
1173
+ ビ|ョ 1172
1174
+ ピ|ョ 1173
1175
+ イ|バ 1174
1176
+ ブ|イ 1175
1177
+ ウ|ブ 1176
1178
+ ア|ル 1177
1179
+ ィ|・ 1178
1180
+ エ|チ 1179
1181
+ オ|ビ 1180
1182
+ マ|ア 1181
1183
+ モ|ア 1182
1184
+ ウ|オ 1183
1185
+ ン|ソ 1184
1186
+ リ|ア 1185
1187
+ バ|イ 1186
1188
+ ヨ|シ 1187
1189
+ ナ|ウ 1188
1190
+ ン|ケ 1189
1191
+ ト|モ 1190
1192
+ ア|ワ 1191
1193
+ オ|ペ 1192
1194
+ ヰ 1193
g2p/japanese_katakana_mfa/meta.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"version": "3.0.0a2.dev0+g940e907.d20230824", "architecture": "phonetisaurus", "train_date": "2023-09-26 10:20:51.329857", "phones": ["k\u02d0", "m\u02b2", "\u027e\u02b2\u02d0", "t\u0255\u02d0", "\u0261\u02d0", "\u027e\u02d0", "v\u02b2", "w", "\u014b", "\u0278\u02d0", "j", "b", "\u0278\u02b2\u02d0", "d\u0291\u02d0", "o\u02d0", "\u025f", "v", "n", "\u0255\u02d0", "h\u02d0", "ts", "b\u02b2", "d\u02b2\u02d0", "\u026f", "e\u02d0", "\u027e", "p\u02d0", "a\u02d0", "\u0294", "s\u02d0", "m\u02b2\u02d0", "t\u02b2", "\u0255", "o", "t\u02d0", "z", "\u0261", "\u0272\u02d0", "k", "i\u02d0", "m", "n\u02d0", "dz", "ts\u02d0", "t", "p\u02b2\u02d0", "dz\u02d0", "p", "\u00e7", "s", "t\u02b2\u02d0", "\u0278\u02b2", "m\u02d0", "h", "\u025f\u02d0", "a", "\u0268", "\u0274", "\u0268\u02d0", "t\u0255", "w\u02d0", "c\u02d0", "\u0274\u02d0", "\u0291", "\u0278", "d\u0291", "\u026f\u02d0", "d", "d\u02d0", "p\u02b2", "\u027e\u02b2", "b\u02b2\u02d0", "d\u02b2", "\u0272", "i", "c", "b\u02d0", "e", "\u00e7\u02d0", "\u0270\u0303"], "graphemes": ["\u30b7", "\u30a1", "\u30ab", "\u30cc", "\u3055", "\u30bc", "\u30b9", "\u3057", "\u30c9", "\u30b4", "\u3074", "\u30a6", "\u30be", "\u306f", "\u3062", "\u30d4", "\u3068", "\u307f", "\u30b0", "\u3082", "\u30f0", "\u30d3", "\u304f", "\u30d5", "\u3049", "\u30b3", "\u30f1", "\u3050", "\u30e6", "\u30df", "\u30c5", "\u307b", "\u3076", "\u30e0", "\u3045", "\u30ae", "\u3063", "\u3052", "\u3089", "\u30dd", "\u305f", "\u30da", "\u3043", "\u30a7", "\u30d8", "\u3065", "\u30ac", "\u30f3", "\u30d0", "\u305c", "\u308a", "\u304b", "\u3041", "\u30e1", "\u30d9", "\u30e3", "\u30db", "\u308b", "\u3087", "\u306c", "\u30ee", "\u30fb", "\u3060", "\u308e", "\u30c3", "\u30b1", "\u30e5", "\u30d6", "\u30ba", "\u304e", "\u307a", "\u3044", "\u30c4", "\u30b8", "\u30ef", "\u30ad", "\u30d2", "\u30aa", "\u30b6", "\u304a", "\u30a8", "\u30f2", "\u307c", "\u3073", "\u30e4", "\u30c1", "\u3081", "\u3091", "\u30d1", "\u30b2", "\u30c8", "\u3061", "\u3072", "\u3093", "\u30ea", "\u30d7", "\u30a3", "\u306e", "\u30a5", "\u30c7", "\u30bf", "\u3083", "\u3078", "\u30fc", "\u3086", "\u3066", "\u3051", "\u30ec", "\u30dc", "\u3048", "\u30eb", "\u3058", "\u3085", "\u3088", "\u30c0", "\u30cb", "\u305b", "\u307e", "\u30cf", "\u30f4", "\u3080", "\u30af", "\u3075", "\u30c2", "\u30bb", "\u30cd", "\u3067", "\u308c", "\u3047", "\u30e8", "\u3077", "\u3069", "\u30ca", "\u3090", "\u306a", "\u3079", "\u30a2", "\u3071", "\u308d", "\u307d", "\u30bd", "\u3056", "\u308f", "\u30a4", "\u304c", "\u3053", "\u3054", "\u305a", "\u30b5", "\u3059", "\u306d", "\u3064", "\u306b", "\u3092", "\u30ce", "\u30e9", "\u305e", "\u30ed", "\u3042", "\u3046", "\u305d", "\u3070", "\u30de", "\u304d", "\u30e7", "\u30c6", "\u30e2", "\u3084", "\u30a9"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "evaluation": {"num_words": 44636, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 401717, "num_graphemes": 169, "num_phones": 80}, "unicode_decomposition": false}
g2p/japanese_katakana_mfa/model.fst ADDED

Git LFS Details

  • SHA256: df5b453dcfdbde6ba3821827ca69011145e954c11e648a9ad2e0b0adf85a3c7e
  • Pointer size: 133 Bytes
  • Size of remote file: 34.8 MB
g2p/japanese_katakana_mfa/phones.sym ADDED
@@ -0,0 +1,81 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <eps> 0
2
+ aː 1
3
+ i 2
4
+ ɯ 3
5
+ ɸ 4
6
+ ɯː 5
7
+ ɲ 6
8
+ e 7
9
+ b 8
10
+ a 9
11
+ k 10
12
+ oː 11
13
+ tː 12
14
+ ɕ 13
15
+ t 14
16
+ ɾ 15
17
+ o 16
18
+ d 17
19
+ m 18
20
+ n 19
21
+ mʲ 20
22
+ j 21
23
+ ɨː 22
24
+ ɴ 23
25
+ ɡ 24
26
+ s 25
27
+ iː 26
28
+ w 27
29
+ eː 28
30
+ ɨ 29
31
+ z 30
32
+ c 31
33
+ ŋ 32
34
+ ɰ̃ 33
35
+ ʑ 34
36
+ ç 35
37
+ tɕ 36
38
+ ts 37
39
+ bʲ 38
40
+ ɟ 39
41
+ ɾʲ 40
42
+ pː 41
43
+ kː 42
44
+ h 43
45
+ cː 44
46
+ sː 45
47
+ dz 46
48
+ dʑ 47
49
+ nː 48
50
+ ɕː 49
51
+ mʲː 50
52
+ mː 51
53
+ pʲ 52
54
+ p 53
55
+ tsː 54
56
+ hː 55
57
+ pʲː 56
58
+ ɡː 57
59
+ ʔ 58
60
+ tɕː 59
61
+ ɲː 60
62
+ tʲ 61
63
+ dʲ 62
64
+ bː 63
65
+ tʲː 64
66
+ ɸʲ 65
67
+ ɴː 66
68
+ dzː 67
69
+ dː 68
70
+ ɸː 69
71
+ dʑː 70
72
+ ɟː 71
73
+ v 72
74
+ vʲ 73
75
+ ɾː 74
76
+ çː 75
77
+ dʲː 76
78
+ wː 77
79
+ ɸʲː 78
80
+ ɾʲː 79
81
+ bʲː 80