Upload folder using huggingface_hub

README.md

@@ -12,7 +12,7 @@ license: cc-by-4.0
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-This MFA model is for aligning Spanish speech.
+This MFA model is for aligning Russian speech.
 
 - [Model details](#model-details)
 - [Uses](#uses)
@@ -185,39 +185,36 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
 - **Source:** https://voice.mozilla.org/en/datasets
 - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
 - **Dialects:** spain, latin america
-- **Number of hours:** 670.81
-- **Number of utterances:** 480,819
-- **Number of speakers:** 22,028
-  - **Female speakers:** 1,198
-  - **Male speakers:** 3,431
-  - **Unknown speakers:** 17,399
-
+- **Number of hours:** 507.00
+- **Number of utterances:** 350,422
+- **Number of speakers:** 16,413
+  - **Female speakers:** 1,308
+  - **Male speakers:** 3,396
+  - **Unknown speakers:** 11,738
 
 #### GlobalPhone Spanish (Latin American)
 
 - **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0203/
 - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
 - **Dialects:** Latin America
-- **Number of hours:** 22.12
-- **Number of utterances:** 6,898
+- **Number of hours:** 22.09
+- **Number of utterances:** 7,049
 - **Number of speakers:** 100
   - **Female speakers:** 56
   - **Male speakers:** 44
   - **Unknown speakers:** 0
 
-
 #### Google i18n Chile
 
 - **Source:** https://openslr.org/71/
 - **License:** [CC BY-SA 4.0](https://creativecommons.org/licenses/by-sa/4.0/)
 - **Dialects:** latin america
-- **Number of hours:** 7.15
+- **Number of hours:** 7.14
 - **Number of utterances:** 4,374
 - **Number of speakers:** 31
-  - **Female speakers:** 13
-  - **Male speakers:** 18
-  - **Unknown speakers:** 0
-
+  - **Female speakers:** 0
+  - **Male speakers:** 0
+  - **Unknown speakers:** 31
 
 #### Google i18n Columbia
 
@@ -227,10 +224,9 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
 - **Number of hours:** 7.58
 - **Number of utterances:** 4,903
 - **Number of speakers:** 33
-  - **Female speakers:** 16
-  - **Male speakers:** 17
-  - **Unknown speakers:** 0
-
+  - **Female speakers:** 0
+  - **Male speakers:** 0
+  - **Unknown speakers:** 33
 
 #### Google i18n Peru
 
@@ -240,11 +236,10 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
 - **Number of hours:** 9.22
 - **Number of utterances:** 5,447
 - **Number of speakers:** 38
-  - **Female speakers:** 18
-  - **Male speakers:** 20
+  - **Female speakers:** 0
+  - **Male speakers:** 0
   - **Unknown speakers:** 0
 
-
 #### Google i18n Puerto Rico
 
 - **Source:** https://openslr.org/71/
@@ -253,10 +248,9 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
 - **Number of hours:** 1.00
 - **Number of utterances:** 617
 - **Number of speakers:** 5
-  - **Female speakers:** 5
+  - **Female speakers:** 0
   - **Male speakers:** 0
-  - **Unknown speakers:** 0
-
+  - **Unknown speakers:** 5
 
 #### Google i18n Venezuela
 
@@ -266,50 +260,46 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
 - **Number of hours:** 4.81
 - **Number of utterances:** 3,357
 - **Number of speakers:** 23
-  - **Female speakers:** 11
-  - **Male speakers:** 12
-  - **Unknown speakers:** 0
-
+  - **Female speakers:** 0
+  - **Male speakers:** 0
+  - **Unknown speakers:** 23
 
 #### Multilingual LibriSpeech Spanish
 
 - **Source:** https://openslr.org/94/
 - **License:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)
 - **Dialects:** spain
-- **Number of hours:** 938.30
-- **Number of utterances:** 225,494
-- **Number of speakers:** 126
+- **Number of hours:** 791.41
+- **Number of utterances:** 1,061,144
+- **Number of speakers:** 300
   - **Female speakers:** 70
   - **Male speakers:** 56
   - **Unknown speakers:** 0
 
-
 #### Multilingual TEDx Spanish
 
 - **Source:** https://www.openslr.org/100/
 - **License:** [CC BY-NC-ND 4.0](https://creativecommons.org/licenses/by-nc-nd/4.0/)
 - **Dialects:** spain, latin america
-- **Number of hours:** 176.18
-- **Number of utterances:** 72,504
-- **Number of speakers:** 1,068
+- **Number of hours:** 155.81
+- **Number of utterances:** 231,851
+- **Number of speakers:** 1,081
   - **Female speakers:** 0
   - **Male speakers:** 0
   - **Unknown speakers:** 1,068
 
-
 #### M-AILABS Spanish
 
 - **Source:** https://openslr.org/94/
 - **License:** [M-AILABS License](https://www.caito.de/2019/01/the-m-ailabs-speech-dataset/)
 - **Dialects:** spain, latin america
-- **Number of hours:** 108.57
-- **Number of utterances:** 59,296
-- **Number of speakers:** 21
+- **Number of hours:** 87.21
+- **Number of utterances:** 48,176
+- **Number of speakers:** 20
   - **Female speakers:** 11
   - **Male speakers:** 10
   - **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 sha256:3c055279ca03284e21f7360b0de0021ab726a703ac72b7dcad6dde2c23d1e9fb
-size 49999629
+oid sha256:7a6d8725c6175551029d288344a1d8a54dd7849a340c309e1f340f1f735bbaae
+size 50003738

acoustic/final.mdl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe4edabec07441fa04b45194de9cd5b98b0689fc36424e9166e0b31d5b4c063
-size 49999629
+oid sha256:d9a2faa1d095b457f3052539b6e5692d2860ea56675c8f3f58bc813ed6832587
+size 50003738

acoustic/meta.json

@@ -1 +1 @@
-{"phones": ["a", "ã", "b", "c", "d̪", "e", "ẽ", "f", "h", "i", "ĩ", "j", "k", "l", "m", "n", "o", "õ", "p", "r", "s", "tʃ", "t̪", "u", "ũ", "v", "w", "x", "z", "ç", "ð", "ŋ", "ɟ", "ɟʝ", "ɡ", "ɣ", "ɱ", "ɲ", "ɾ", "ʃ", "ʎ", "ʝ", "β", "θ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "ã": 4, "b": 5, "c": 6, "d̪": 7, "e": 8, "ẽ": 9, "f": 10, "h": 11, "i": 12, "ĩ": 13, "j": 14, "k": 15, "l": 16, "m": 17, "n": 18, "o": 19, "õ": 20, "p": 21, "r": 22, "s": 23, "tʃ": 24, "t̪": 25, "u": 26, "ũ": 27, "v": 28, "w": 29, "x": 30, "z": 31, "ç": 32, "ð": 33, "ŋ": 34, "ɟ": 35, "ɟʝ": 36, "ɡ": 37, "ɣ": 38, "ɱ": 39, "ɲ": 40, "ɾ": 41, "ʃ": 42, "ʎ": 43, "ʝ": 44, "β": 45, "θ": 46}, "phone_groups": {"0": ["b"], "1": ["c"], "2": ["d̪"], "3": ["f"], "4": ["v"], "5": ["j"], "6": ["k"], "7": ["l"], "8": ["ʎ"], "9": ["m"], "10": ["ɱ"], "11": ["n"], "12": ["p"], "13": ["r"], "14": ["s"], "15": ["h"], "16": ["z"], "17": ["tʃ"], "18": ["t̪"], "19": ["w"], "20": ["x"], "21": ["ç"], "22": ["ð"], "23": ["ŋ"], "24": ["ɟ"], "25": ["ɟʝ"], "26": ["ɡ"], "27": ["ɣ"], "28": ["ɲ"], "29": ["ɾ"], "30": ["ʃ"], "31": ["θ"], "32": ["ʝ"], "33": ["β"], "34": ["a"], "35": ["ã"], "36": ["o"], "37": ["õ"], "38": ["e"], "39": ["ẽ"], "40": ["i"], "41": ["ĩ"], "42": ["u"], "43": ["ũ"]}, "version": "3.3.0", "architecture": "gmm-hmm", "train_date": "2026-05-27 06:47:16.598778", "training": {"audio_duration": 5729959.612768349, "num_speakers": 18044, "num_utterances": 1715580, "num_oovs": 0, "average_log_likelihood": -52.92090465162847}, "dictionaries": {"names": ["spanish_latin_america_mfa", "spanish_spain_mfa"], "default": "default", "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": 0.12, "initial_silence_probability": 0.12, "final_silence_correction": 0.99, "final_non_silence_correction": 0.3066666666666667, "duration_information": {"a": [0.07950576387973216, 0.04456792743374035], "ã": [0.0702442787207905, 0.02628163881491706], "b": [0.05828549062947206, 0.022849146529341505], "c": [0.06608248414515139, 0.021592284392363582], "ç": [0.09154359967572119, 0.03066930342445189], "d̪": [0.05054221208766195, 0.021345025277722314], "ð": [0.04024252968394246, 0.03026071910319262], "e": [0.06788913113126024, 0.043385080816281694], "ẽ": [0.06313937244681508, 0.02839465785020889], "f": [0.08916967541204014, 0.034408610420908405], "ɣ": [0.06792618383262798, 0.0272026906079282], "ɡ": [0.05755239406926764, 0.023953648717286266], "h": [0.10728033450459988, 0.05401506738862812], "i": [0.07504648510987048, 0.039193988528544256], "ĩ": [0.06784324436942, 0.029196927552299967], "j": [0.061261362636104745, 0.028296378358252314], "ɟ": [0.07482364341868625, 0.09758764356125346], "ʝ": [0.08852919997902424, 0.029293727405957447], "ɟʝ": [0.07453079457715608, 0.031884615472690406], "k": [0.07203690514350027, 0.0237530818149648], "l": [0.06559476024654949, 0.032269918384138944], "m": [0.0716070349956483, 0.02490384552849163], "ɱ": [0.06103377928804851, 0.022116343146030476], "n": [0.06999126449651596, 0.03591584213082867], "ɲ": [0.07325190835232596, 0.03174832803435645], "ŋ": [0.05845463086186727, 0.033061284557546956], "o": [0.08105202223367128, 0.0501990888519406], "õ": [0.06556388552019854, 0.0283476447646692], "p": [0.06544058616826011, 0.026631117560876712], "r": [0.07850147888362365, 0.03660539086836448], "ɾ": [0.06098193004199082, 0.030135946386184734], "s": [0.08975516506807305, 0.04382980548918615], "ʃ": [0.12320884015144416, 0.08474962947777238], "t̪": [0.06592018504083619, 0.024333876305927024], "tʃ": [0.10829766645172373, 0.02782868707948267], "u": [0.07232394157285872, 0.03595637428546263], "ũ": [0.0717810062073453, 0.034358624146501905], "v": [0.09346633474032084, 0.04697565046779673], "w": [0.058499655143201115, 0.027058141971586864], "x": [0.10470706284404506, 0.03085151149814256], "ʎ": [0.06276035598803956, 0.021411706912200356], "z": [0.07911509547631183, 0.02969901734174867], "β": [0.06005503098590085, 0.019038171631017432], "θ": [0.09229441882311844, 0.02795855493259604]}}
+{"phones": ["a", "ã", "b", "c", "d̪", "e", "ẽ", "f", "h", "i", "ĩ", "j", "k", "l", "m", "n", "o", "õ", "p", "r", "s", "tʃ", "t̪", "u", "ũ", "v", "w", "x", "z", "ç", "ð", "ŋ", "ɟ", "ɟʝ", "ɡ", "ɣ", "ɱ", "ɲ", "ɾ", "ʃ", "ʎ", "ʝ", "β", "θ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "ã": 4, "b": 5, "c": 6, "d̪": 7, "e": 8, "ẽ": 9, "f": 10, "h": 11, "i": 12, "ĩ": 13, "j": 14, "k": 15, "l": 16, "m": 17, "n": 18, "o": 19, "õ": 20, "p": 21, "r": 22, "s": 23, "tʃ": 24, "t̪": 25, "u": 26, "ũ": 27, "v": 28, "w": 29, "x": 30, "z": 31, "ç": 32, "ð": 33, "ŋ": 34, "ɟ": 35, "ɟʝ": 36, "ɡ": 37, "ɣ": 38, "ɱ": 39, "ɲ": 40, "ɾ": 41, "ʃ": 42, "ʎ": 43, "ʝ": 44, "β": 45, "θ": 46}, "phone_groups": {}, "version": "3.4.3", "architecture": "gmm-hmm", "train_date": "2026-10-11 19:14:43.519833", "training": {"audio_duration": 5729187.885305747, "num_speakers": 18044, "num_utterances": 1715460, "num_oovs": 0, "average_log_likelihood": -53.34040768053771}, "dictionaries": {"names": ["spanish_latin_america_mfa", "spanish_spain_mfa"], "default": "spanish_latin_america_mfa", "silence_word": "<eps>", "oov_word": "<unk>", "bracketed_word": "[bracketed]", "laughter_word": "[laughter]", "clitic_marker": null, "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": false, "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": 0.2866666666666666, "initial_silence_probability": 0.5, "final_silence_correction": null, "final_non_silence_correction": null, "duration_information": {"a": [-2.6417864734659418, 0.4765473699887165], "ã": [-2.6864494980700586, 0.37266985586466644], "b": [-2.845048471191826, 0.3766992200088064], "c": [-2.7562112097546865, 0.3176817313418639], "d̪": [-2.9837243712630963, 0.37201447181510294], "e": [-2.8092795438600646, 0.4780201514528625], "ẽ": [-2.6050489669641097, 0.4967613426186338], "f": [-2.430869204741879, 0.3896606213671831], "h": [-2.369919146674856, 0.44540503695454164], "i": [-4.107820787218895, 0.825816589123414], "ĩ": [-2.6186876914598582, 0.4763636671300368], "j": [-2.8670538671113093, 0.42705874767458685], "k": [-2.65161028342027, 0.34270434520552046], "l": [-2.790741883249864, 0.4117030950218088], "m": [-2.640940547884888, 0.35557666804072624], "n": [-3.152277345013469, 0.8494897568039963], "o": [-2.6630771721455284, 0.5123590070146551], "õ": [-2.7364443881028424, 0.4086270501511866], "p": [-2.8202590846723132, 0.38024585059880633], "r": [-2.656528020209877, 0.4349416854880715], "s": [-2.4666358855915655, 0.4694086609299233], "tʃ": [-2.221708010447016, 0.2758270160329022], "t̪": [-2.710278306424458, 0.34291288070641407], "u": [-2.7463954008375184, 0.4275997918613659], "ũ": [-2.6878182477831345, 0.4597277806271973], "v": [-2.3935349817711518, 0.5619587393924218], "w": [-2.924133354736119, 0.4090783813665612], "x": [-2.276646408774064, 0.3469380552619876], "z": [-2.4730605106340744, 0.409826417448127], "ç": [-2.329784791632472, 0.3680534336687106], "ð": [-2.85821844191737, 0.5225704246160691], "ŋ": [-4.604077611306815, 0.052226171463055], "ɟ": [-2.748666726698342, 0.5564347153201166], "ɟʝ": [-2.685140906098043, 0.37524840803321247], "ɡ": [-2.8954763629134197, 0.3445438754585867], "ɣ": [-2.721461278128654, 0.3821539411765106], "ɱ": [-2.8957785248529313, 0.2867526612169351], "ɲ": [-2.475645090783068, 0.42868207830844546], "ɾ": [-2.8498926917132597, 0.3968407960772254], "ʃ": [-2.2433216097765714, 0.4783075742093697], "ʎ": [-2.503459866107921, 0.3953817646414917], "ʝ": [-2.3792980480342507, 0.3633714914291954], "β": [-2.758360298143314, 0.3823720829037817], "θ": [-2.3489056479892003, 0.3023214497445763]}}

acoustic/tree

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98444067fec7d9549a876a06b59fb7d4ef421b8f9458fe05b0089295dab5b6a9
-size 280653
+oid sha256:923ca33810b65ec60e45d34cf14df90dd220e6dc4a4db6675d66d7db10239ec7
+size 302617

dictionary/rules.yaml

@@ -1,244 +1,252 @@
 dialects:
   latin_america:
   - following_context: $
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.84
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: s
-    silence_after_probability: 0.06
-    silence_before_correction: 0.77
+    silence_after_probability: 0.09
+    silence_before_correction: -7.6
   - following_context: $
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.84
     preceding_context: ''
     probability: 0.01
     replacement: h
     segment: s
-    silence_after_probability: 0.64
-    silence_before_correction: 0.75
+    silence_after_probability: 0.59
+    silence_before_correction: -7.62
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.1
+    non_silence_before_correction: 0.86
     preceding_context: ''
     probability: 0.01
     replacement: h
     segment: s
-    silence_after_probability: 0.38
-    silence_before_correction: 0.83
+    silence_after_probability: 0.36
+    silence_before_correction: -7.91
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.87
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: s
-    silence_after_probability: 0.3
-    silence_before_correction: 0.78
+    silence_after_probability: 0.32
+    silence_before_correction: -7.92
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.21
+    non_silence_before_correction: 0.74
     preceding_context: ^
     probability: 0.01
     replacement: e s
     segment: s
-    silence_after_probability: 0.75
-    silence_before_correction: 0.92
+    silence_after_probability: 0.81
+    silence_before_correction: -8.0
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.13
+    non_silence_before_correction: 0.91
     preceding_context: ^
     probability: 0.01
     replacement: e z
     segment: z
-    silence_after_probability: 0.81
-    silence_before_correction: 0.87
+    silence_after_probability: 0.86
+    silence_before_correction: -8.13
   - following_context: ''
-    non_silence_before_correction: -0.06
+    non_silence_before_correction: 0.8
     preceding_context: ^
     probability: 0.01
     replacement: ''
     segment: x
-    silence_after_probability: 0.26
-    silence_before_correction: 0.77
+    silence_after_probability: 0.38
+    silence_before_correction: -7.81
   - following_context: $
-    non_silence_before_correction: -0.08
+    non_silence_before_correction: 0.88
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: ɾ
-    silence_after_probability: 0.11
-    silence_before_correction: 0.8
+    silence_after_probability: 0.26
+    silence_before_correction: -8.02
   - following_context: $
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.9
     preceding_context: ''
     probability: 0.01
     replacement: r
     segment: ɾ
-    silence_after_probability: 0.36
-    silence_before_correction: 0.77
+    silence_after_probability: 0.3
+    silence_before_correction: -8.05
   - following_context: $
-    non_silence_before_correction: -0.1
+    non_silence_before_correction: 0.85
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: '[ŋnmɲ]'
-    silence_after_probability: 0.07
-    silence_before_correction: 0.83
+    silence_after_probability: 0.28
+    silence_before_correction: -7.91
   - following_context: $
-    non_silence_before_correction: -0.11
+    non_silence_before_correction: 0.87
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: ð
-    silence_after_probability: 0.28
-    silence_before_correction: 0.86
+    silence_after_probability: 0.24
+    silence_before_correction: -8.05
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.86
     preceding_context: '[aiouejw]'
     probability: 0.01
     replacement: r
     segment: ɾ
-    silence_after_probability: 0.41
-    silence_before_correction: 0.79
+    silence_after_probability: 0.35
+    silence_before_correction: -7.8
   - following_context: '[aiouejw]'
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.86
     preceding_context: '[^aiouejw]'
     probability: 0.01
     replacement: r
     segment: ɾ
-    silence_after_probability: 0.24
-    silence_before_correction: 0.78
+    silence_after_probability: 0.25
+    silence_before_correction: -7.87
   - following_context: '[^ij]'
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.86
     preceding_context: ''
     probability: 0.01
     replacement: ɲ j
     segment: ɲ
-    silence_after_probability: 0.41
-    silence_before_correction: 0.77
+    silence_after_probability: 0.43
+    silence_before_correction: -7.79
   - following_context: ''
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.84
     preceding_context: ''
     probability: 0.01
     replacement: ʃ
     segment: ʝ
-    silence_after_probability: 0.38
-    silence_before_correction: 0.79
+    silence_after_probability: 0.4
+    silence_before_correction: -7.76
   - following_context: ''
-    non_silence_before_correction: -0.24
+    non_silence_before_correction: 0.82
     preceding_context: ''
     probability: 0.01
     replacement: ʃ
     segment: ɟʝ
-    silence_after_probability: 0.34
-    silence_before_correction: 1.1
+    silence_after_probability: 0.33
+    silence_before_correction: -7.8
   spain:
   - following_context: $
-    non_silence_before_correction: -0.08
+    non_silence_before_correction: 0.82
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: s
-    silence_after_probability: 0.11
-    silence_before_correction: 0.79
+    silence_after_probability: 0.1
+    silence_before_correction: -7.57
   - following_context: $
-    non_silence_before_correction: -0.06
+    non_silence_before_correction: 0.85
     preceding_context: ''
     probability: 0.01
     replacement: h
     segment: s
-    silence_after_probability: 0.26
-    silence_before_correction: 0.72
+    silence_after_probability: 0.2
+    silence_before_correction: -7.64
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.87
     preceding_context: ''
     probability: 0.01
     replacement: h
     segment: s
-    silence_after_probability: 0.19
-    silence_before_correction: 0.79
+    silence_after_probability: 0.2
+    silence_before_correction: -7.91
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.09
+    non_silence_before_correction: 0.85
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: s
-    silence_after_probability: 0.21
-    silence_before_correction: 0.85
+    silence_after_probability: 0.29
+    silence_before_correction: -7.88
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.14
+    non_silence_before_correction: 0.94
     preceding_context: ^
     probability: 0.01
     replacement: e s
     segment: s
-    silence_after_probability: 0.76
-    silence_before_correction: 0.9
+    silence_after_probability: 0.99
+    silence_before_correction: -8.27
+  - following_context: '[^aiouejw]'
+    non_silence_before_correction: 0.9
+    preceding_context: ^
+    probability: 0.01
+    replacement: e z
+    segment: z
+    silence_after_probability: 0.34
+    silence_before_correction: -8.12
   - following_context: ''
-    non_silence_before_correction: -0.3
+    non_silence_before_correction: 0.83
     preceding_context: ^
     probability: 0.01
     replacement: ''
     segment: x
-    silence_after_probability: 0.81
-    silence_before_correction: 1.51
+    silence_after_probability: 0.6
+    silence_before_correction: -7.85
   - following_context: $
-    non_silence_before_correction: -0.08
+    non_silence_before_correction: 0.89
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: ɾ
-    silence_after_probability: 0.28
-    silence_before_correction: 0.85
+    silence_after_probability: 0.18
+    silence_before_correction: -8.02
   - following_context: $
-    non_silence_before_correction: -0.05
+    non_silence_before_correction: 0.91
     preceding_context: ''
     probability: 0.01
     replacement: r
     segment: ɾ
-    silence_after_probability: 0.2
-    silence_before_correction: 0.73
+    silence_after_probability: 0.22
+    silence_before_correction: -8.1
   - following_context: $
-    non_silence_before_correction: -0.11
+    non_silence_before_correction: 0.87
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: '[ŋnmɲ]'
-    silence_after_probability: 0.05
-    silence_before_correction: 0.87
+    silence_after_probability: 0.03
+    silence_before_correction: -7.92
   - following_context: $
-    non_silence_before_correction: -0.09
+    non_silence_before_correction: 0.88
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: ð
-    silence_after_probability: 0.35
-    silence_before_correction: 0.82
+    silence_after_probability: 0.26
+    silence_before_correction: -8.06
   - following_context: '[^aiouejw]'
-    non_silence_before_correction: -0.06
+    non_silence_before_correction: 0.87
     preceding_context: '[aiouejw]'
     probability: 0.01
     replacement: r
     segment: ɾ
-    silence_after_probability: 0.26
-    silence_before_correction: 0.76
+    silence_after_probability: 0.28
+    silence_before_correction: -7.82
   - following_context: '[aiouejw]'
-    non_silence_before_correction: -0.07
+    non_silence_before_correction: 0.87
     preceding_context: '[^aiouejw]'
     probability: 0.01
     replacement: r
     segment: ɾ
-    silence_after_probability: 0.22
-    silence_before_correction: 0.77
+    silence_after_probability: 0.23
+    silence_before_correction: -7.88
   - following_context: ''
-    non_silence_before_correction: -0.09
+    non_silence_before_correction: 0.85
     preceding_context: ''
     probability: 0.01
     replacement: s
     segment: θ
-    silence_after_probability: 0.29
-    silence_before_correction: 0.85
+    silence_after_probability: 0.31
+    silence_before_correction: -7.76
   - following_context: $
-    non_silence_before_correction: -0.09
+    non_silence_before_correction: 0.92
     preceding_context: ''
     probability: 0.01
     replacement: ''
     segment: θ
-    silence_after_probability: 0.33
-    silence_before_correction: 0.84
+    silence_after_probability: 0.19
+    silence_before_correction: -8.21
 rules: []

dictionary/spanish_spain_mfa.dict

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5411a205babd9dff04577ca58f1d364f86fbb3bb75d7dd1902922a81eef19831
-size 11332945
+oid sha256:45f259ecc2df26fe0181748404dc62dbecd4e70b4f44e818f2d086e4963795a1
+size 11322305

g2p/spanish_latin_america_mfa/meta.json

@@ -1 +1 @@
-{"version": "3.2.0", "architecture": "phonetisaurus", "train_date": "2024-09-15 16:51:13.487039", "phones": ["z", "o", "o\u0303", "t\u0283", "n", "j", "e", "\u025f", "b", "\u027e", "\u03b2", "\u014b", "\u0271", "\u0261", "\u025f\u029d", "r", "i\u0303", "w", "t\u032a", "l", "v", "i", "u\u0303", "c", "d\u032a", "\u028e", "\u029d", "x", "\u0283", "m", "s", "a\u0303", "f", "\u00e7", "p", "k", "e\u0303", "\u00f0", "\u0263", "u", "a", "\u0272"], "graphemes": ["'", "\u0303", "\u0302", "z", "o", "n", "j", "e", "b", "q", "\u0308", "d", "g", "r", "\u00fc", "\u00f3", "l", "w", "v", "h", "\u00ed", "i", "c", "x", "m", "s", "f", "\u00fa", "k", "p", "\u00e1", "\u00e9", "\u0301", "t", "u", "y", "\u00f1", "a"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": true, "evaluation": {"num_words": 11776, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 139675, "num_graphemes": 38, "num_phones": 42}}
+{"version": "3.2.0", "architecture": "phonetisaurus", "train_date": "2024-09-15 16:51:13.487039", "phones": ["\u027e", "v", "l", "\u028e", "o\u0303", "\u0261", "u\u0303", "\u00f0", "\u029d", "e\u0303", "i", "\u0271", "e", "t\u032a", "i\u0303", "k", "d\u032a", "s", "n", "\u025f", "u", "w", "m", "z", "o", "\u025f\u029d", "\u0272", "t\u0283", "x", "\u0263", "a", "f", "p", "r", "\u00e7", "\u014b", "\u03b2", "\u0283", "j", "a\u0303", "c", "b"], "graphemes": ["v", "\u0302", "l", "y", "c", "'", "\u00f1", "i", "\u0301", "e", "h", "\u00e9", "k", "g", "s", "d", "n", "t", "u", "\u00fc", "w", "m", "\u00fa", "z", "\u0308", "o", "\u00e1", "\u00f3", "\u0303", "x", "a", "f", "r", "p", "q", "j", "\u00ed", "b"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": true, "evaluation": {"num_words": 11776, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 139675, "num_graphemes": 38, "num_phones": 42}}

g2p/spanish_spain_mfa/meta.json

@@ -1 +1 @@
-{"version": "3.2.0", "architecture": "phonetisaurus", "train_date": "2024-09-15 16:26:51.342202", "phones": ["z", "o", "o\u0303", "t\u0283", "n", "j", "e", "\u025f", "b", "\u027e", "\u03b2", "\u014b", "\u0271", "\u0261", "\u025f\u029d", "r", "i\u0303", "w", "t\u032a", "l", "v", "i", "u\u0303", "c", "d\u032a", "\u028e", "\u029d", "x", "\u0283", "m", "\u03b8", "s", "a\u0303", "f", "\u00e7", "p", "k", "e\u0303", "\u00f0", "\u0263", "u", "a", "\u0272"], "graphemes": ["'", "\u0303", "\u0302", "z", "o", "n", "j", "e", "b", "q", "\u0308", "d", "g", "r", "\u00fc", "\u00f3", "l", "w", "v", "h", "\u00ed", "i", "c", "x", "m", "s", "f", "\u00fa", "k", "p", "\u00e1", "\u00e9", "\u0301", "t", "u", "y", "\u00f1", "a"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": true, "evaluation": {"num_words": 11790, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 139661, "num_graphemes": 38, "num_phones": 43}}
+{"version": "3.2.0", "architecture": "phonetisaurus", "train_date": "2024-09-15 16:26:51.342202", "phones": ["\u027e", "v", "l", "\u028e", "o\u0303", "\u0261", "u\u0303", "\u00f0", "\u029d", "e\u0303", "i", "\u0271", "e", "t\u032a", "i\u0303", "k", "d\u032a", "s", "n", "\u025f", "u", "w", "m", "z", "o", "\u025f\u029d", "\u0272", "\u03b8", "t\u0283", "x", "\u0263", "a", "f", "p", "r", "\u00e7", "\u014b", "\u03b2", "\u0283", "j", "a\u0303", "c", "b"], "graphemes": ["v", "\u0302", "l", "y", "c", "'", "\u00f1", "i", "\u0301", "e", "h", "\u00e9", "k", "g", "s", "d", "n", "t", "u", "\u00fc", "w", "m", "\u00fa", "z", "\u0308", "o", "\u00e1", "\u00f3", "\u0303", "x", "a", "f", "r", "p", "q", "j", "\u00ed", "b"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": true, "evaluation": {"num_words": 11790, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 139661, "num_graphemes": 38, "num_phones": 43}}