Upload folder using huggingface_hub

README.md

@@ -133,40 +133,37 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
 - **Source:** http://www.openslr.org/57/
 - **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
 - **Dialects:** N/A
-- **Number of hours:** 19.93
-- **Number of utterances:** 16,656
+- **Number of hours:** 15.40
+- **Number of utterances:** 16,638
 - **Number of speakers:** 233
   - **Female speakers:** 0
   - **Male speakers:** 0
   - **Unknown speakers:** 233
 
-
 #### Common Voice French
 
 - **Source:** https://voice.mozilla.org/en/datasets
 - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
 - **Dialects:** N/A
 - **Number of hours:** 963.62
-- **Number of utterances:** 697,672
+- **Number of utterances:** 697,671
 - **Number of speakers:** 17,312
   - **Female speakers:** 814
   - **Male speakers:** 3,323
   - **Unknown speakers:** 13,175
 
-
 #### GlobalPhone French
 
 - **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0197/
 - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
 - **Dialects:** N/A
-- **Number of hours:** 26.95
-- **Number of utterances:** 10,476
+- **Number of hours:** 26.94
+- **Number of utterances:** 10,474
 - **Number of speakers:** 100
   - **Female speakers:** 51
   - **Male speakers:** 49
   - **Unknown speakers:** 0
 
-
 ### Training Procedure
 
 <!-- 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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79fdc8bd29928688687d5038c33f51757e4af8ef8a7d9a86a3c6e925cd03585d
-size 50025401
+oid sha256:3429163d2e647c7bc079c9a2acf5ac4a9ac644eb5f36831dc657ccc67bdcbc11
+size 50016888

acoustic/final.mdl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43365b5a83eb4909e3a51429c614e194d4c1076db79317c9b971e52a2bb663fa
-size 50025401
+oid sha256:ef239bac5e7a2699fd61df69821c61dfceb4d643ca95dd4bfed2c8ffe06f8265
+size 50016888

acoustic/meta.json

@@ -1 +1 @@
-{"phones": ["a", "b", "c", "d", "dʒ", "e", "f", "i", "j", "k", "l", "m", "mʲ", "n", "o", "p", "s", "t", "ts", "tʃ", "u", "v", "w", "y", "z", "ø", "ŋ", "œ", "ɑ", "ɑ̃", "ɔ", "ɔ̃", "ə", "ɛ", "ɛ̃", "ɟ", "ɡ", "ɥ", "ɲ", "ʁ", "ʃ", "ʎ", "ʒ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "b": 4, "c": 5, "d": 6, "dʒ": 7, "e": 8, "f": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "mʲ": 15, "n": 16, "o": 17, "p": 18, "s": 19, "t": 20, "ts": 21, "tʃ": 22, "u": 23, "v": 24, "w": 25, "y": 26, "z": 27, "ø": 28, "ŋ": 29, "œ": 30, "ɑ": 31, "ɑ̃": 32, "ɔ": 33, "ɔ̃": 34, "ə": 35, "ɛ": 36, "ɛ̃": 37, "ɟ": 38, "ɡ": 39, "ɥ": 40, "ɲ": 41, "ʁ": 42, "ʃ": 43, "ʎ": 44, "ʒ": 45}, "phone_groups": {"0": ["b"], "1": ["d"], "2": ["dʒ"], "3": ["f"], "4": ["c", "k"], "5": ["l", "ʎ"], "6": ["m", "mʲ"], "7": ["n"], "8": ["ɲ"], "9": ["p"], "10": ["s"], "11": ["t"], "12": ["ts"], "13": ["tʃ"], "14": ["v"], "15": ["ɟ", "ɡ"], "16": ["ɥ"], "17": ["ʁ"], "18": ["ʃ"], "19": ["ʒ"], "20": ["z"], "21": ["ŋ"], "22": ["a"], "23": ["e"], "24": ["i", "j"], "25": ["o"], "26": ["u", "w"], "27": ["y"], "28": ["ø"], "29": ["œ"], "30": ["ɑ"], "31": ["ɑ̃"], "32": ["ɔ"], "33": ["ɔ̃"], "34": ["ə"], "35": ["ɛ"], "36": ["ɛ̃"]}, "version": "3.3.0", "architecture": "gmm-hmm", "train_date": "2026-06-06 13:03:55.417475", "training": {"audio_duration": 3604787.6700496906, "num_speakers": 17645, "num_utterances": 718496, "num_oovs": 0, "average_log_likelihood": -52.166970996403414}, "dictionaries": {"names": ["french_mfa"], "default": "french_mfa", "silence_word": "<eps>", "oov_word": "<unk>", "bracketed_word": "[bracketed]", "laughter_word": "[laughter]", "clitic_marker": "'", "position_dependent_phones": false}, "language": "unknown", "tokenization": "simple", "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": 0.23, "initial_silence_probability": 0.23, "final_silence_correction": 0.99, "final_non_silence_correction": 0.01, "duration_information": {"a": [0.08265242366413862, 0.044203288104389074], "b": [0.07980701352053822, 0.03284664582570673], "c": [0.09305004406662995, 0.03320914268896061], "d": [0.07659231417423525, 0.034480501631442936], "dʒ": [0.12757988165198028, 0.04552474552833763], "e": [0.0913201493924777, 0.05223426083187632], "f": [0.11812115360719026, 0.04435650072042205], "i": [0.0856484578514421, 0.04671309175128047], "j": [0.05647140109513491, 0.04480205722329379], "k": [0.08918321439587164, 0.04602862569746411], "l": [0.07541823100880603, 0.03941067701680916], "m": [0.08590028771086534, 0.0360433060431074], "mʲ": [0.08341564119072122, 0.03822670679834245], "n": [0.08770868018142476, 0.04525996511520973], "o": [0.10634103327948338, 0.05612691332612411], "p": [0.07698034128235663, 0.03284311721161856], "s": [0.12306795822424602, 0.049214709511110136], "t": [0.08310344265665723, 0.04137609807578321], "ts": [0.20072441063527985, 0.10837367701689674], "tʃ": [0.18222788490918226, 0.07704997388629506], "u": [0.07827945260097244, 0.046536333748124215], "v": [0.08212461790541728, 0.03686858581897214], "w": [0.06944147495729236, 0.03541174482614757], "y": [0.07774269477795452, 0.04403000814260385], "z": [0.09455392540941943, 0.04109608602944559], "ø": [0.08039180512267466, 0.05212702701332507], "ŋ": [0.13901000674072417, 0.07435110232005733], "œ": [0.09181485564917682, 0.053678622700911185], "ɑ": [0.12589858775952056, 0.07398102891480127], "ɑ̃": [0.11333734538996572, 0.05057739621988574], "ɔ": [0.0748445109354859, 0.03564019360013516], "ɔ̃": [0.1093392114355376, 0.04972547587972984], "ə": [0.02715321120231902, 0.04941907759143581], "ɛ": [0.08517729789429346, 0.04740051902142103], "ɛ̃": [0.11148430894761713, 0.05322408037711459], "ɟ": [0.09271726391987545, 0.03868947556040995], "ɡ": [0.07672037363470333, 0.03653533290598031], "ɥ": [0.07514218142454526, 0.03533681224902736], "ɲ": [0.09143539350400214, 0.048685956747953736], "ʁ": [0.08817401413669833, 0.04239879642560741], "ʃ": [0.14650922218333495, 0.052901585380433915], "ʎ": [0.06801155255511082, 0.04775666352041967], "ʒ": [0.10265953231536433, 0.04070088352075846]}}
+{"phones": ["a", "b", "c", "d", "dʒ", "e", "f", "i", "j", "k", "l", "m", "mʲ", "n", "o", "p", "s", "t", "ts", "tʃ", "u", "v", "w", "y", "z", "ø", "ŋ", "œ", "ɑ", "ɑ̃", "ɔ", "ɔ̃", "ə", "ɛ", "ɛ̃", "ɟ", "ɡ", "ɥ", "ɲ", "ʁ", "ʃ", "ʎ", "ʒ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "b": 4, "c": 5, "d": 6, "dʒ": 7, "e": 8, "f": 9, "i": 10, "j": 11, "k": 12, "l": 13, "m": 14, "mʲ": 15, "n": 16, "o": 17, "p": 18, "s": 19, "t": 20, "ts": 21, "tʃ": 22, "u": 23, "v": 24, "w": 25, "y": 26, "z": 27, "ø": 28, "ŋ": 29, "œ": 30, "ɑ": 31, "ɑ̃": 32, "ɔ": 33, "ɔ̃": 34, "ə": 35, "ɛ": 36, "ɛ̃": 37, "ɟ": 38, "ɡ": 39, "ɥ": 40, "ɲ": 41, "ʁ": 42, "ʃ": 43, "ʎ": 44, "ʒ": 45}, "phone_groups": {"0": ["b"], "1": ["d"], "2": ["dʒ"], "3": ["f"], "4": ["c", "k"], "5": ["l", "ʎ"], "6": ["m", "mʲ"], "7": ["n"], "8": ["ɲ"], "9": ["p"], "10": ["s"], "11": ["t"], "12": ["ts"], "13": ["tʃ"], "14": ["v"], "15": ["ɟ", "ɡ"], "16": ["ɥ"], "17": ["ʁ"], "18": ["ʃ"], "19": ["ʒ"], "20": ["z"], "21": ["ŋ"], "22": ["a"], "23": ["e"], "24": ["i", "j"], "25": ["o"], "26": ["u", "w"], "27": ["y"], "28": ["ø"], "29": ["œ"], "30": ["ɑ"], "31": ["ɑ̃"], "32": ["ɔ"], "33": ["ɔ̃"], "34": ["ə"], "35": ["ɛ"], "36": ["ɛ̃"]}, "version": "3.4.3", "architecture": "gmm-hmm", "train_date": "2026-10-14 01:13:39.603860", "training": {"audio_duration": 3613253.436030918, "num_speakers": 17645, "num_utterances": 720042, "num_oovs": 0, "average_log_likelihood": -52.40341251359973}, "dictionaries": {"names": ["french_mfa"], "default": "french_mfa", "silence_word": "<eps>", "oov_word": "<unk>", "bracketed_word": "[bracketed]", "laughter_word": "[laughter]", "clitic_marker": "'", "position_dependent_phones": false}, "language": "unknown", "tokenization": "simple", "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": 0.23, "initial_silence_probability": 0.23, "final_silence_correction": 0.99, "final_non_silence_correction": 0.01, "duration_information": {"a": [-2.6216335265641844, 0.44917200029173193], "b": [-2.602154006786768, 0.3771887833240205], "c": [-2.4175886162884073, 0.3565071836255449], "d": [-2.642053927217856, 0.40071062171079574], "dʒ": [-2.094497557294508, 0.3607390561899618], "e": [-2.549971495806736, 0.512217948634519], "f": [-2.2002483742266974, 0.37131182418962017], "i": [-2.600665873887732, 0.479305880585026], "j": [-3.2002875232932917, 0.8765697189020197], "k": [-2.4959816001161013, 0.4375881940453779], "l": [-2.696199602242986, 0.4482578840972223], "m": [-2.535812315158846, 0.3745228590817993], "mʲ": [-2.696625855719598, 0.39561981213191233], "n": [-2.5548063891949604, 0.4436768616893721], "o": [-2.3694049601959413, 0.4914677888443901], "p": [-2.610412969729707, 0.4122547996584863], "s": [-2.177720095940548, 0.41127811716483487], "t": [-2.558968324583762, 0.43056680831702104], "ts": [-1.7452121611374292, 0.5353740015702657], "tʃ": [-1.7648380405012072, 0.43761411981195336], "u": [-2.7069496533639796, 0.5099065378162813], "v": [-2.595199617521127, 0.4187276614574978], "w": [-2.796808003790142, 0.47259618585464064], "y": [-2.67452017788932, 0.481697636926046], "z": [-2.4352870413366516, 0.4056609729712329], "ø": [-2.7061044249390727, 0.5479262729175591], "ŋ": [-2.156604989783453, 0.5673865400251464], "œ": [-2.5164772207763635, 0.5374441986138476], "ɑ": [-2.3150273416575273, 0.5783722151712771], "ɑ̃": [-2.2781525838001717, 0.42852214384475873], "ɔ": [-2.7049308145197166, 0.4218960330816298], "ɔ̃": [-2.3403823181311236, 0.43295000293504343], "ə": [-3.416045906335412, 0.6197669561738761], "ɛ": [-2.6058591474532378, 0.50920476597467], "ɛ̃": [-2.319236583488177, 0.4438478675422758], "ɟ": [-2.387277615279964, 0.36565496205742826], "ɡ": [-2.676293763844007, 0.3935455532450124], "ɥ": [-2.877383779787644, 0.4576132916611105], "ɲ": [-2.4993895746987422, 0.47917743560360215], "ʁ": [-2.5452957194090318, 0.4239320299784563], "ʃ": [-1.9940962024024684, 0.35200055408155145], "ʎ": [-2.880054967166227, 0.7814899464554792], "ʒ": [-2.348910435866832, 0.3834682349772001]}}

acoustic/tree

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f947ac3360f801086572ee217f7e62a76821445588a2f46303f1f16796763418
-size 283877
+oid sha256:b8782ca89b88867e5a1f25a1422c91031a66f1d19fd52825e0f7c2e8707c6127
+size 288349

dictionary/rules.yaml

@@ -1,19 +1,19 @@
 dialects:
   us:
   - following_context: $
-    non_silence_before_correction: -0.01
+    non_silence_before_correction: 0.0
     preceding_context: '[^aeiouyøœɑɔəɛ̃]+'
-    probability: 0.45
+    probability: 0.52
     replacement: ʁ ə
     segment: ʁ
-    silence_after_probability: 0.4
+    silence_after_probability: 0.3
     silence_before_correction: 0.02
   - following_context: '[^i]'
     non_silence_before_correction: 0.01
     preceding_context: ''
-    probability: 0.49
+    probability: 0.54
     replacement: n j
     segment: ɲ
-    silence_after_probability: 1.24
-    silence_before_correction: -0.02
+    silence_after_probability: 1.0
+    silence_before_correction: -0.01
 rules: []

g2p/french_mfa/graphemes.txt

@@ -2,342 +2,342 @@
 |	1
 _	2
 a	3
-c|e	4
-s	5
-d	6
-l	7
-m	8
-e|s	9
-ô	10
-b	11
-a|u	12
-x	13
-'	14
-b|o	15
-r	16
-e|r	17
-'|i	18
-l|a	19
-'|l	20
-e	21
-n|n	22
-'|s	23
-c|h	24
-a|d	25
-o|r	26
-f	27
-g|a	28
-r|d	29
-g|e	30
-h|e	31
-a|i	32
-a|l	33
-a|n	34
-s|e	35
-g	36
-e|n	37
-l|i	38
-y|a	39
-h	40
-t	41
-t|o	42
-n	43
-l|é	44
-n|i	45
-r|a	46
-f|a	47
-k|o	48
-c	49
-a|r	50
-d|a	51
-b|u	52
-r|g	53
-t|r	54
-a|w	55
-h|u	56
-r|i	57
-c|i	58
-k	59
-s|h	60
-n|e	61
-n|o	62
-o|n	63
-r|o	64
-v|i	65
-t|h	66
-t|i	67
-s|i	68
-s|t	69
-t|a	70
-v	71
-v|a	72
-s|a	73
-v|o	74
-z	75
-b|a	76
-u|i	77
-o|u	78
-i	79
-n|é	80
-c|a	81
-c|o	82
-t|é	83
-c|u	84
-l|e	85
-d|i	86
-ñ|o	87
-d|è	88
-u|m	89
-h|a	90
-i|n	91
-l|l	92
-o|i	93
-s|s	94
-b|l	95
-n|t	96
-t|s	97
-m|e	98
-u|r	99
-è|r	100
-é	101
-é|e	102
-é|s	103
-j	104
-k|i	105
-l|o	106
-d|o	107
-a|s	108
-e|z	109
-â|t	110
-q|u	111
-g|i	112
-r|e	113
-î	114
-î|t	115
-t|e	116
-t|t	117
-e|u	118
-t|u	119
-t|z	120
-í	121
-i|a	122
-a|y	123
-y|e	124
-a|z	125
-z|a	126
-ï	127
-b|b	128
-a|g	129
-n|a	130
-d|e	131
-e|m	132
-u	133
-e|y	134
-e|a	135
-h|i	136
-o	137
-f|o	138
-u|e	139
-y	140
-â|n	141
-è|s	142
-é|c	143
-è	144
-c|é	145
-a|h	146
-e|l	147
-z|i	148
-m|i	149
-j|e	150
-k|a	151
-k|e	152
-b|i	153
-m|a	154
-j|i	155
-e|k	156
-w|a	157
-r|r	158
-m|y	159
-p	160
-o|l	161
-m|è	162
-d|u	163
-â|h	164
-q|a	165
-d|y	166
-ü	167
-b|e	168
-e|i	169
-k|u	170
-w|y	171
-o|m	172
-b|y	173
-e|e	174
-h|y	175
-â|m	176
-r|é	177
-r|y	178
-e|t	179
-v|e	180
-h|o	181
-ë|n	182
-d|j	183
-d|s	184
-g|é	185
-j|a	186
-m|é	187
-e|c	188
-n|g	189
-i|o	190
-j|u	191
-k|h	192
-z|e	193
-l|u	194
-ï|a	195
-f|f	196
-m|m	197
-d|é	198
-g|è	199
-f|i	200
-u|x	201
-t|c	202
-o|y	203
-y|è	204
-b|r	205
-m|o	206
-w|i	207
-s|é	208
-g|o	209
-v|é	210
-o|t	211
-s|o	212
-ñ|i	213
-r|u	214
-z|z	215
-c|c	216
-b|s	217
-o|d	218
-l|y	219
-b|é	220
-d|r	221
-n|u	222
-g|h	223
-w|e	224
-á	225
-z|u	226
-b|â	227
-ê|t	228
-a|m	229
-p|a	230
-a|c	231
-p|h	232
-o|s	233
-s|u	234
-p|u	235
-a|b	236
-p|e	237
-u|a	238
-u|é	239
-u|o	240
-p|i	241
-i|m	242
-c|k	243
-g|n	244
-p|l	245
-s|c	246
-û|t	247
-i|l	248
-m|u	249
-t|y	250
-o|p	251
-ï|e	252
-p|o	253
-q	254
-y|l	255
-p|p	256
-o|o	257
-ú	258
-p|t	259
-f|r	260
-e|d	261
-i|e	262
-ç|a	263
-i|è	264
-p|è	265
-a|e	266
-h|é	267
-v|è	268
-ú|n	269
-u|n	270
-g|u	271
-ñ|a	272
-c|y	273
-z|o	274
-z|è	275
-f|é	276
-œ	277
-w	278
-w|s	279
-s|p	280
-o|ï	281
-y|o	282
-d|d	283
-j|o	284
-l|d	285
-d|h	286
-h|è	287
-k|é	288
-u|l	289
-n|c	290
-g|y	291
-c|t	292
-f|e	293
-u|s	294
-û	295
-f|l	296
-w|n	297
-f|u	298
-â	299
-c|l	300
-ç	301
-n|d	302
-g|g	303
-i|u	304
-e|v	305
-o|g	306
-g|l	307
-ë	308
-ö|n	309
-o|b	310
-l|t	311
-g|r	312
-g|s	313
-g|t	314
-p|é	315
-m|b	316
-â|r	317
-e|f	318
-z|y	319
-ü|e	320
-s|y	321
-w|o	322
-'|h	323
-'|a	324
-u|k	325
-a|k	326
-i|é	327
-o|v	328
-k|k	329
-k|n	330
-y|n	331
-u|z	332
-v|á	333
-à	334
-o|c	335
-ï|n	336
-u|c	337
-s|k	338
-á|n	339
+'	4
+b|o	5
+r	6
+d	7
+e|r	8
+'|i	9
+l|a	10
+s	11
+'|l	12
+e	13
+n|n	14
+'|s	15
+c|h	16
+a|d	17
+o|r	18
+f	19
+g|a	20
+r|d	21
+g|e	22
+h|e	23
+a|i	24
+a|l	25
+a|n	26
+s|e	27
+g	28
+e|n	29
+l|i	30
+y|a	31
+h	32
+t	33
+t|o	34
+n	35
+l|é	36
+n|i	37
+r|a	38
+f|a	39
+k|o	40
+c	41
+a|r	42
+a|u	43
+b	44
+d|a	45
+m	46
+b|u	47
+r|g	48
+t|r	49
+a|w	50
+h|u	51
+r|i	52
+c|i	53
+k	54
+s|h	55
+n|e	56
+n|o	57
+o|n	58
+r|o	59
+v|i	60
+t|h	61
+t|i	62
+s|i	63
+s|t	64
+t|a	65
+v	66
+v|a	67
+s|a	68
+v|o	69
+z	70
+b|a	71
+u|i	72
+o|u	73
+i	74
+n|é	75
+c|a	76
+c|o	77
+t|é	78
+c|u	79
+l|e	80
+d|i	81
+ñ|o	82
+d|è	83
+u|m	84
+h|a	85
+i|n	86
+l|l	87
+o|i	88
+s|s	89
+b|l	90
+e|s	91
+n|t	92
+t|s	93
+m|e	94
+u|r	95
+è|r	96
+é	97
+é|e	98
+é|s	99
+j	100
+k|i	101
+l	102
+l|o	103
+d|o	104
+a|s	105
+e|z	106
+â|t	107
+q|u	108
+g|i	109
+r|e	110
+î	111
+î|t	112
+t|e	113
+t|t	114
+e|u	115
+t|u	116
+t|z	117
+í	118
+x	119
+i|a	120
+a|y	121
+y|e	122
+a|z	123
+z|a	124
+ï	125
+b|b	126
+a|g	127
+n|a	128
+d|e	129
+e|m	130
+u	131
+e|y	132
+e|a	133
+h|i	134
+o	135
+f|o	136
+u|e	137
+y	138
+â|n	139
+è|s	140
+é|c	141
+è	142
+c|é	143
+a|h	144
+e|l	145
+z|i	146
+m|i	147
+j|e	148
+k|a	149
+k|e	150
+b|i	151
+m|a	152
+j|i	153
+e|k	154
+w|a	155
+r|r	156
+m|y	157
+p	158
+o|l	159
+m|è	160
+d|u	161
+â|h	162
+q|a	163
+d|y	164
+ü	165
+b|e	166
+e|i	167
+c|e	168
+k|u	169
+w|y	170
+o|m	171
+b|y	172
+e|e	173
+h|y	174
+â|m	175
+r|é	176
+r|y	177
+e|t	178
+v|e	179
+h|o	180
+ë|n	181
+d|j	182
+d|s	183
+g|é	184
+j|a	185
+m|é	186
+e|c	187
+n|g	188
+i|o	189
+j|u	190
+k|h	191
+z|e	192
+l|u	193
+ï|a	194
+f|f	195
+m|m	196
+d|é	197
+g|è	198
+f|i	199
+u|x	200
+t|c	201
+o|y	202
+y|è	203
+b|r	204
+m|o	205
+w|i	206
+s|é	207
+g|o	208
+v|é	209
+o|t	210
+s|o	211
+ñ|i	212
+r|u	213
+z|z	214
+b|s	215
+o|d	216
+l|y	217
+b|é	218
+d|r	219
+n|u	220
+g|h	221
+w|e	222
+á	223
+z|u	224
+b|â	225
+ê|t	226
+a|m	227
+p|a	228
+a|c	229
+p|h	230
+o|s	231
+s|u	232
+p|u	233
+c|c	234
+a|b	235
+p|e	236
+u|a	237
+u|é	238
+u|o	239
+p|i	240
+i|m	241
+c|k	242
+g|n	243
+p|l	244
+s|c	245
+û|t	246
+i|l	247
+m|u	248
+t|y	249
+o|p	250
+ï|e	251
+p|o	252
+q	253
+y|l	254
+p|p	255
+o|o	256
+ú	257
+p|t	258
+f|r	259
+e|d	260
+i|e	261
+ç|a	262
+i|è	263
+p|è	264
+a|e	265
+h|é	266
+v|è	267
+ú|n	268
+u|n	269
+g|u	270
+ñ|a	271
+c|y	272
+z|o	273
+z|è	274
+f|é	275
+œ	276
+w	277
+w|s	278
+s|p	279
+o|ï	280
+y|o	281
+d|d	282
+j|o	283
+l|d	284
+d|h	285
+h|è	286
+k|é	287
+u|l	288
+n|c	289
+g|y	290
+c|t	291
+f|e	292
+u|s	293
+û	294
+f|l	295
+w|n	296
+f|u	297
+â	298
+c|l	299
+ç	300
+n|d	301
+g|g	302
+i|u	303
+e|v	304
+o|g	305
+g|l	306
+ë	307
+ö|n	308
+o|b	309
+l|t	310
+g|r	311
+g|s	312
+g|t	313
+p|é	314
+m|b	315
+â|r	316
+e|f	317
+z|y	318
+ü|e	319
+s|y	320
+w|o	321
+'|h	322
+'|a	323
+u|k	324
+a|k	325
+i|é	326
+o|v	327
+k|k	328
+k|n	329
+y|n	330
+u|z	331
+v|á	332
+à	333
+o|c	334
+ï|n	335
+u|c	336
+s|k	337
+á|n	338
+ô	339
 a|o	340
 d|g	341
 u|y	342
@@ -426,29 +426,29 @@ x|t	424
 î|l	425
 ñ|u	426
 i|s	427
-ö|r	428
-j|n	429
-ö	430
-i|x	431
-ö|h	432
-ö|m	433
-â|b	434
+ö	428
+i|x	429
+ö|r	430
+j|n	431
+â|b	432
+ö|h	433
+ö|m	434
 a|t	435
 ô|l	436
 u|p	437
-n|s	438
-w|c	439
-x|i	440
-j|é	441
-j|ö	442
-w|k	443
-u|f	444
-j|k	445
-e|o	446
-a|v	447
-o|f	448
-ë|t	449
-z|n	450
+x|i	438
+j|é	439
+j|ö	440
+w|k	441
+n|s	442
+u|f	443
+j|k	444
+e|o	445
+w|c	446
+ë|t	447
+z|n	448
+a|v	449
+o|f	450
 ê|l	451
 ü|l	452
 ö|w	453
@@ -469,14 +469,14 @@ p|ê	465
 i|c	468
 ï|l	469
 a|ï	470
-'|r	471
-i|d	472
+i|d	471
+'|r	472
 w|l	473
 e|b	474
 '|o	475
 k|w	476
-ö|g	477
-v|s	478
+v|s	477
+ö|g	478
 y|s	479
 ñ|í	480
 ë|v	481
@@ -495,8 +495,8 @@ w|é	493
 y|d	494
 x|o	495
 w|r	496
-h|l	497
-o|x	498
+o|x	497
+h|l	498
 i|p	499
 h|n	500
 â|g	501
@@ -541,12 +541,12 @@ k|l	537
 ö|z	540
 ü|p	541
 ë|c	542
-ö|y	543
-ü|d	544
-à|h	545
+à|h	543
+ö|y	544
+ü|d	545
 ü|é	546
-y|k	547
-ô|d	548
+ô|d	547
+y|k	548
 i|k	549
 â|c	550
 œ|d	551
@@ -562,11 +562,11 @@ z|l	558
 i|q	561
 á|t	562
 k|s	563
-ó|w	564
-ù|l	565
-ê|v	566
-í|o	567
-ù|m	568
+ù|l	564
+ê|v	565
+í|o	566
+ù|m	567
+ó|w	568
 i|f	569
 ö|p	570
 i|v	571

g2p/french_mfa/meta.json

@@ -1 +1 @@
-{"version": "3.3.0", "architecture": "phonetisaurus", "train_date": "2026-06-06 13:26:40.014800", "phones": ["a", "b", "c", "d", "d\u0292", "e", "f", "i", "j", "k", "l", "m", "m\u02b2", "n", "o", "p", "s", "t", "ts", "t\u0283", "u", "v", "w", "y", "z", "\u00f8", "\u014b", "\u0153", "\u0251", "\u0251\u0303", "\u0254", "\u0254\u0303", "\u0259", "\u025b", "\u025b\u0303", "\u025f", "\u0261", "\u0265", "\u0272", "\u0281", "\u0283", "\u028e", "\u0292"], "graphemes": ["\u00e7", "x", "\u00ea", "n", "w", "\u00f4", "\u00f6", "j", "\u00eb", "\u00e0", "u", "t", "z", "h", "g", "s", "m", "q", "\u00e9", "\u00e2", "\u00ed", "l", "\u00f3", "f", "c", "k", "\u00fc", "\u0153", "i", "o", "\u00ef", "b", "\u00e8", "e", "\u00fb", "\u00f9", "r", "\u00e1", "\u00fa", "\u00ee", "p", "\u00f1", "'", "y", "d", "v", "a"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": false, "evaluation": {"num_words": 23398, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 210595, "num_graphemes": 47, "num_phones": 43}}
+{"version": "3.4.3", "architecture": "phonetisaurus", "train_date": "2026-10-14 01:54:22.959140", "phones": ["a", "b", "c", "d", "d\u0292", "e", "f", "i", "j", "k", "l", "m", "m\u02b2", "n", "o", "p", "s", "t", "ts", "t\u0283", "u", "v", "w", "y", "z", "\u00f8", "\u014b", "\u0153", "\u0251", "\u0251\u0303", "\u0254", "\u0254\u0303", "\u0259", "\u025b", "\u025b\u0303", "\u025f", "\u0261", "\u0265", "\u0272", "\u0281", "\u0283", "\u028e", "\u0292"], "graphemes": ["\u00ee", "i", "\u00e8", "\u00f6", "f", "j", "y", "a", "\u00fb", "\u00e1", "c", "k", "e", "v", "b", "z", "w", "\u0153", "\u00f1", "\u00ef", "s", "q", "x", "m", "\u00e0", "u", "o", "d", "\u00e7", "'", "\u00f9", "\u00ea", "t", "\u00e9", "n", "p", "\u00fa", "\u00fc", "\u00e2", "r", "l", "g", "\u00f3", "h", "\u00ed", "\u00f4", "\u00eb"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": false, "evaluation": {"num_words": 23398, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 210595, "num_graphemes": 47, "num_phones": 43}}

g2p/french_mfa/phones.txt

@@ -1,29 +1,29 @@
 <eps>	0
 a	1
-s	2
-d	3
-l	4
-m	5
-o	6
-b	7
-ɔ	8
-ʁ	9
-e	10
-i	11
-ʎ	12
-n	13
-tʃ	14
-f	15
-ɡ	16
-ʒ	17
-ɑ̃	18
-ɛ	19
-z	20
-j	21
-t	22
-ɲ	23
-ɛ̃	24
-k	25
+b	2
+ɔ	3
+ʁ	4
+d	5
+e	6
+i	7
+l	8
+ʎ	9
+n	10
+s	11
+tʃ	12
+f	13
+ɡ	14
+ʒ	15
+ɑ̃	16
+ɛ	17
+z	18
+j	19
+t	20
+o	21
+ɲ	22
+ɛ̃	23
+k	24
+m	25
 u	26
 y	27
 ʃ	28