mmcauliffe commited on
Commit
1e1e9a2
·
verified ·
1 Parent(s): b219494

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -75,7 +75,7 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
75
  #### Details for ukrainian_mfa dictionary and G2P model
76
 
77
  - **Source:** wikipron
78
- - **Orthography:** Latin
79
  - **Phone set:** MFA
80
  - **Words:** 158,578
81
  * **Phones:** 83
@@ -133,34 +133,30 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
133
  - **Male speakers:** 260
134
  - **Unknown speakers:** 636
135
 
136
-
137
  #### GlobalPhone Ukrainian
138
 
139
  - **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0377/
140
  - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
141
  - **Dialects:** N/A
142
  - **Number of hours:** 14.11
143
- - **Number of utterances:** 12,814
144
  - **Number of speakers:** 119
145
  - **Female speakers:** 72
146
  - **Male speakers:** 47
147
  - **Unknown speakers:** 0
148
 
149
-
150
  #### M-AILABS Ukrainian
151
 
152
  - **Source:** https://openslr.org/94/
153
  - **License:** [M-AILABS License](https://www.caito.de/2019/01/the-m-ailabs-speech-dataset/)
154
  - **Dialects:** N/A
155
  - **Number of hours:** 83.22
156
- - **Number of utterances:** 34,189
157
  - **Number of speakers:** 6
158
  - **Female speakers:** 5
159
  - **Male speakers:** 1
160
  - **Unknown speakers:** 0
161
 
162
-
163
-
164
  ### Training Procedure
165
 
166
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
75
  #### Details for ukrainian_mfa dictionary and G2P model
76
 
77
  - **Source:** wikipron
78
+ - **Orthography:** Cyrillic
79
  - **Phone set:** MFA
80
  - **Words:** 158,578
81
  * **Phones:** 83
 
133
  - **Male speakers:** 260
134
  - **Unknown speakers:** 636
135
 
 
136
  #### GlobalPhone Ukrainian
137
 
138
  - **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0377/
139
  - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
140
  - **Dialects:** N/A
141
  - **Number of hours:** 14.11
142
+ - **Number of utterances:** 12,813
143
  - **Number of speakers:** 119
144
  - **Female speakers:** 72
145
  - **Male speakers:** 47
146
  - **Unknown speakers:** 0
147
 
 
148
  #### M-AILABS Ukrainian
149
 
150
  - **Source:** https://openslr.org/94/
151
  - **License:** [M-AILABS License](https://www.caito.de/2019/01/the-m-ailabs-speech-dataset/)
152
  - **Dialects:** N/A
153
  - **Number of hours:** 83.22
154
+ - **Number of utterances:** 34,185
155
  - **Number of speakers:** 6
156
  - **Female speakers:** 5
157
  - **Male speakers:** 1
158
  - **Unknown speakers:** 0
159
 
 
 
160
  ### Training Procedure
161
 
162
  <!-- 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:d03f863ca95256c7173fd33dbb46370dadca511ecd30d3e414aaa886f6976146
3
- size 33565560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89db1a9f44a4a6d326691ad7bd3a9ef1e701f86768b094e2451b9fb2a98ca20c
3
+ size 33550993
acoustic/final.mdl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5437ed04b4a48ac86723fcf16b4d4cff409db6673ebc8849d880f7c166bbe47b
3
- size 33565560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90683f455094e8e0b53aaac5f44c1d47456d3e2d977d9d580630c49714a93272
3
+ size 33550993
acoustic/lda.mat CHANGED
Binary files a/acoustic/lda.mat and b/acoustic/lda.mat differ
 
acoustic/meta.json CHANGED
@@ -1 +1 @@
1
- {"phones": ["b", "bʲ", "bʲː", "bː", "c", "cː", "dzʲ", "dʒ", "dʲ", "dʲː", "d̪", "d̪z̪", "d̪z̪ː", "d̪ː", "e", "f", "fʲ", "fː", "i", "iː", "j", "k", "kː", "l", "lː", "m", "mʲ", "mʲː", "n̪", "n̪ː", "o", "p", "pʲ", "pʲː", "sʲ", "sʲː", "s̪", "s̪ː", "tsʲ", "tsʲː", "tʃ", "tʃʲ", "tʃʲː", "tʃː", "tʲ", "tʲː", "t̪", "t̪s̪", "t̪s̪ː", "t̪ː", "u", "x", "zʲ", "zʲː", "z̪", "z̪ː", "ç", "ɐ", "ɑ", "ɔ", "ɛ", "ɟ", "ɡ", "ɡː", "ɦ", "ɦː", "ɪ", "ɲ", "ɲː", "ɾ", "ɾʲ", "ɾʲː", "ɾː", "ʃ", "ʃʲ", "ʃʲː", "ʊ", "ʋ", "ʋʲ", "ʋʲː", "ʋː", "ʎ", "ʎː", "ʒ", "ʒʲ", "ʒʲː", "ʝ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "b": 3, "bʲ": 4, "bʲː": 5, "bː": 6, "c": 7, "cː": 8, "dzʲ": 9, "dʒ": 10, "dʲ": 11, "dʲː": 12, "d̪": 13, "d̪z̪": 14, "d̪z̪ː": 15, "d̪ː": 16, "e": 17, "f": 18, "fʲ": 19, "fː": 20, "i": 21, "iː": 22, "j": 23, "k": 24, "kː": 25, "l": 26, "lː": 27, "m": 28, "mʲ": 29, "mʲː": 30, "n̪": 31, "n̪ː": 32, "o": 33, "p": 34, "pʲ": 35, "pʲː": 36, "sʲ": 37, "sʲː": 38, "s̪": 39, "s̪ː": 40, "tsʲ": 41, "tsʲː": 42, "tʃ": 43, "tʃʲ": 44, "tʃʲː": 45, "tʃː": 46, "tʲ": 47, "tʲː": 48, "t̪": 49, "t̪s̪": 50, "t̪s̪ː": 51, "t̪ː": 52, "u": 53, "x": 54, "zʲ": 55, "zʲː": 56, "z̪": 57, "z̪ː": 58, "ç": 59, "ɐ": 60, "ɑ": 61, "ɔ": 62, "ɛ": 63, "ɟ": 64, "ɡ": 65, "ɡː": 66, "ɦ": 67, "ɦː": 68, "ɪ": 69, "ɲ": 70, "ɲː": 71, "ɾ": 72, "ɾʲ": 73, "ɾʲː": 74, "ɾː": 75, "ʃ": 76, "ʃʲ": 77, "ʃʲː": 78, "ʊ": 79, "ʋ": 80, "ʋʲ": 81, "ʋʲː": 82, "ʋː": 83, "ʎ": 84, "ʎː": 85, "ʒ": 86, "ʒʲ": 87, "ʒʲː": 88, "ʝ": 89}, "phone_groups": {"0": ["b", "bʲ", "bʲː", "bː"], "1": ["c", "cː", "k", "kː"], "2": ["ɟ", "ɡ", "ɡː"], "3": ["dzʲ", "dʒ"], "4": ["dʲ", "dʲː", "d̪", "d̪ː"], "5": ["d̪z̪", "d̪z̪ː"], "6": ["f", "fʲ", "fː"], "7": ["j"], "8": ["l", "lː", "ʎ", "ʎː"], "9": ["m", "mʲ", "mʲː"], "10": ["n̪", "n̪ː", "ɲ", "ɲː"], "11": ["p", "pʲ", "pʲː"], "12": ["sʲ", "sʲː", "s̪", "s̪ː"], "13": ["tsʲ", "tsʲː", "t̪s̪", "t̪s̪ː"], "14": ["tʃ", "tʃʲ", "tʃʲː", "tʃː"], "15": ["tʲ", "tʲː", "t̪", "t̪ː"], "16": ["x", "ç"], "17": ["ɦ", "ɦː", "ʝ"], "18": ["zʲ", "zʲː", "z̪", "z̪ː"], "19": ["ɾ", "ɾʲ", "ɾʲː", "ɾː"], "20": ["ʒ", "ʒʲ", "ʒʲː"], "21": ["ʃ", "ʃʲ", "ʃʲː"], "22": ["ʋ", "ʋʲ", "ʋʲː", "ʋː"], "23": ["ɐ", "ɑ"], "24": ["e"], "25": ["i", "iː"], "26": ["o", "ɔ"], "27": ["ɛ"], "28": ["ɪ"], "29": ["u", "ʊ"]}, "version": "3.3.0", "architecture": "gmm-hmm", "train_date": "2026-06-05 08:33:06.468394", "training": {"audio_duration": 686379.9441552133, "num_speakers": 1151, "num_utterances": 119422, "num_oovs": 0, "average_log_likelihood": -55.61127311151342}, "dictionaries": {"names": ["ukrainian_mfa"], "default": "ukrainian_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": 0.25, "initial_silence_probability": 0.25, "final_silence_correction": 0.99, "final_non_silence_correction": 0.01, "duration_information": {"b": [0.08373695821870013, 0.027207796079878842], "bʲ": [0.08628548588626203, 0.025823615620635586], "bʲː": [0.1816667119661967, 0.02639456472273516], "bː": [0.10750001668930054, 0.022173662124267857], "c": [0.10250999239179849, 0.02817719532915039], "cː": [0.14499998092651367, 0.02121318320510914], "dzʲ": [0.08784546726348673, 0.058416313725633884], "dʒ": [0.11408529267064736, 0.0438146861211376], "dʲ": [0.08127509769991538, 0.029225514079223264], "dʲː": [0.1388118767944893, 0.03762259622837246], "d̪": [0.07677277119490959, 0.026546637084614404], "d̪z̪": [0.0803434495726529, 0.04072343166052931], "d̪z̪ː": [0.19714303527559554, 0.23019654274332174], "d̪ː": [0.12712263962570228, 0.04133228108513304], "e": [0.06403925254824112, 0.03559831173254384], "f": [0.11007586025771532, 0.035360437942213274], "fʲ": [0.10799851376352654, 0.034081020304146434], "fː": [0.0975000262260437, 0.05909020946241937], "i": [0.08766422746233782, 0.052006156549104746], "iː": [0.11931317280294056, 0.06103863089230157], "j": [0.07679002269819422, 0.04269252669514438], "k": [0.09326922035643907, 0.030420566803151708], "kː": [0.1558333362142245, 0.06486892850425616], "l": [0.07532975332493792, 0.025592698526222445], "lː": [0.10167053950358433, 0.03600377865882288], "m": [0.08374355183313639, 0.030034287433925572], "mʲ": [0.0797966628042279, 0.023546133610614528], "mʲː": [0.09166666297685533, 0.034775698147027204], "n̪": [0.07047946881495608, 0.026175021457779588], "n̪ː": [0.12513929551805475, 0.03920773397933639], "pʲː": [0.1300000101327896, 0.008164958022903542], "ʒʲː": [0.13728260896776034, 0.03781183385221139], "ʝ": [0.02290364616298272, 0.029615470627182488], "o": [0.06524697448162615, 0.033618693862746976], "p": [0.0841011131390079, 0.029372909706488922], "pʲ": [0.0803020458831701, 0.028428360803343843], "sʲ": [0.10642310384575666, 0.0416323372868134], "sʲː": [0.12407456812623655, 0.041670638122076144], "s̪": [0.10663819555707284, 0.03950703114771825], "s̪ː": [0.158854179084301, 0.05938047124564071], "tsʲ": [0.1292665951509576, 0.03916851631763394], "tsʲː": [0.1444745896048403, 0.05075288267664146], "tʃ": [0.10081325412589894, 0.04402729414655915], "tʃʲ": [0.12420562332589938, 0.043018552875752715], "tʃʲː": [0.17298467776605062, 0.04197210043409034], "tʃː": [0.17388889015230358, 0.051005373165246656], "tʲ": [0.09448039459185484, 0.04441003920673443], "tʲː": [0.15697821646991617, 0.04939213141051686], "t̪": [0.08415351733796154, 0.03142863811310326], "t̪s̪": [0.12014091558836835, 0.036873332658985514], "t̪s̪ː": [0.1463635888966647, 0.034138709843058695], "t̪ː": [0.16563560043351125, 0.03982968945312366], "u": [0.08758885125392056, 0.04582895951470311], "x": [0.10494772611741048, 0.04234276847594617], "zʲ": [0.09020076766757883, 0.03531105336703904], "zʲː": [0.1258974380982228, 0.04727954885389198], "z̪": [0.08793986904677667, 0.03289769915702138], "z̪ː": [0.12839286792136373, 0.06402967880536366], "ç": [0.11443048982605525, 0.04188773563793815], "ɐ": [0.07592547600097704, 0.04404460423356977], "ɑ": [0.09203953817778025, 0.04651602648233976], "ɔ": [0.07760986213867037, 0.042663448295577305], "ɛ": [0.08523966824759949, 0.05114139514936287], "ɟ": [0.08714284215654645, 0.033523302464060885], "ɡ": [0.0829815894502438, 0.03563834743635261], "ɦ": [0.07884719278655783, 0.03801894439936584], "ɪ": [0.07865362898236088, 0.0463390023528793], "ɲ": [0.07252837386850111, 0.029150650842082942], "ɲː": [0.11272909105743856, 0.03875197888207287], "ɾ": [0.062442956392906104, 0.02447068332469981], "ɾʲ": [0.02422283778125041, 0.025337287730635292], "ɾʲː": [0.049576568292872526, 0.019757094768914817], "ɾː": [0.12153844191477849, 0.06817207987143041], "ʃ": [0.11788327293157314, 0.04400537998076219], "ʃʲ": [0.13005712310763948, 0.0337574843506692], "ʊ": [0.07817757118734256, 0.045920930337808225], "ʋ": [0.07259949879502936, 0.03338986628411191], "ʋʲ": [0.01373668261589795, 0.025329313763984933], "ʋʲː": [0.08482015025701455, 0.04921634946791158], "ʋː": [0.13063675311815895, 0.05018111405102779], "ʎ": [0.010237523113190362, 0.0059238957940766146], "ʎː": [0.022769242926285817, 0.02374447847509161], "ʒ": [0.08451708510613358, 0.03047406746578085], "ʒʲ": [0.10329160605322718, 0.03291518516836559]}}
 
1
+ {"phones": ["b", "bʲ", "bʲː", "bː", "c", "cː", "dzʲ", "dʒ", "dʲ", "dʲː", "d̪", "d̪z̪", "d̪z̪ː", "d̪ː", "e", "f", "fʲ", "fː", "i", "iː", "j", "k", "kː", "l", "lː", "m", "mʲ", "mʲː", "n̪", "n̪ː", "o", "p", "pʲ", "pʲː", "sʲ", "sʲː", "s̪", "s̪ː", "tsʲ", "tsʲː", "tʃ", "tʃʲ", "tʃʲː", "tʃː", "tʲ", "tʲː", "t̪", "t̪s̪", "t̪s̪ː", "t̪ː", "u", "x", "zʲ", "zʲː", "z̪", "z̪ː", "ç", "ɐ", "ɑ", "ɔ", "ɛ", "ɟ", "ɡ", "ɡː", "ɦ", "ɦː", "ɪ", "ɲ", "ɲː", "ɾ", "ɾʲ", "ɾʲː", "ɾː", "ʃ", "ʃʲ", "ʃʲː", "ʊ", "ʋ", "ʋʲ", "ʋʲː", "ʋː", "ʎ", "ʎː", "ʒ", "ʒʲ", "ʒʲː", "ʝ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "b": 3, "bʲ": 4, "bʲː": 5, "bː": 6, "c": 7, "cː": 8, "dzʲ": 9, "dʒ": 10, "dʲ": 11, "dʲː": 12, "d̪": 13, "d̪z̪": 14, "d̪z̪ː": 15, "d̪ː": 16, "e": 17, "f": 18, "fʲ": 19, "fː": 20, "i": 21, "iː": 22, "j": 23, "k": 24, "kː": 25, "l": 26, "lː": 27, "m": 28, "mʲ": 29, "mʲː": 30, "n̪": 31, "n̪ː": 32, "o": 33, "p": 34, "pʲ": 35, "pʲː": 36, "sʲ": 37, "sʲː": 38, "s̪": 39, "s̪ː": 40, "tsʲ": 41, "tsʲː": 42, "tʃ": 43, "tʃʲ": 44, "tʃʲː": 45, "tʃː": 46, "tʲ": 47, "tʲː": 48, "t̪": 49, "t̪s̪": 50, "t̪s̪ː": 51, "t̪ː": 52, "u": 53, "x": 54, "zʲ": 55, "zʲː": 56, "z̪": 57, "z̪ː": 58, "ç": 59, "ɐ": 60, "ɑ": 61, "ɔ": 62, "ɛ": 63, "ɟ": 64, "ɡ": 65, "ɡː": 66, "ɦ": 67, "ɦː": 68, "ɪ": 69, "ɲ": 70, "ɲː": 71, "ɾ": 72, "ɾʲ": 73, "ɾʲː": 74, "ɾː": 75, "ʃ": 76, "ʃʲ": 77, "ʃʲː": 78, "ʊ": 79, "ʋ": 80, "ʋʲ": 81, "ʋʲː": 82, "ʋː": 83, "ʎ": 84, "ʎː": 85, "ʒ": 86, "ʒʲ": 87, "ʒʲː": 88, "ʝ": 89}, "phone_groups": {"0": ["b", "bʲ", "bʲː", "bː"], "1": ["c", "cː", "k", "kː"], "2": ["ɟ", "ɡ", "ɡː"], "3": ["dzʲ", "dʒ"], "4": ["dʲ", "dʲː", "d̪", "d̪ː"], "5": ["d̪z̪", "d̪z̪ː"], "6": ["f", "fʲ", "fː"], "7": ["j"], "8": ["l", "lː", "ʎ", "ʎː"], "9": ["m", "mʲ", "mʲː"], "10": ["n̪", "n̪ː", "ɲ", "ɲː"], "11": ["p", "pʲ", "pʲː"], "12": ["sʲ", "sʲː", "s̪", "s̪ː"], "13": ["tsʲ", "tsʲː", "t̪s̪", "t̪s̪ː"], "14": ["tʃ", "tʃʲ", "tʃʲː", "tʃː"], "15": ["tʲ", "tʲː", "t̪", "t̪ː"], "16": ["x", "ç"], "17": ["ɦ", "ɦː", "ʝ"], "18": ["zʲ", "zʲː", "z̪", "z̪ː"], "19": ["ɾ", "ɾʲ", "ɾʲː", "ɾː"], "20": ["ʒ", "ʒʲ", "ʒʲː"], "21": ["ʃ", "ʃʲ", "ʃʲː"], "22": ["ʋ", "ʋʲ", "ʋʲː", "ʋː"], "23": ["ɐ", "ɑ"], "24": ["e"], "25": ["i", "iː"], "26": ["o", "ɔ"], "27": ["ɛ"], "28": ["ɪ"], "29": ["u", "ʊ"]}, "version": "3.4.3", "architecture": "gmm-hmm", "train_date": "2026-10-12 19:30:25.091284", "training": {"audio_duration": 686680.1841927198, "num_speakers": 1151, "num_utterances": 119442, "num_oovs": 0, "average_log_likelihood": -55.41181657228513}, "dictionaries": {"names": ["ukrainian_mfa"], "default": "ukrainian_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": 0.25, "initial_silence_probability": 0.25, "final_silence_correction": 0.99, "final_non_silence_correction": 0.01, "duration_information": {"b": [-2.4983779514391373, 0.3288681284202348], "bʲ": [-2.4908856393396728, 0.3044688415874466], "bʲː": [-1.7159201095342613, 0.1596699809888687], "bː": [-2.2889635036424463, 0.1745247400894727], "c": [-2.3329225840988346, 0.30670148441492256], "cː": [-1.9364012687854626, 0.1468230812985011], "dzʲ": [-2.566256147812084, 0.5481237538100276], "dʒ": [-2.2506128209135166, 0.43384409940149193], "dʲ": [-2.555272817296946, 0.35152334480495306], "dʲː": [-2.0250761170271683, 0.3186283899446778], "d̪": [-2.60860023905632, 0.33579574106881566], "d̪z̪": [-2.547426380695695, 0.38117226178120445], "d̪z̪ː": [-2.1106370391795664, 0.9435003595106859], "d̪ː": [-2.126489592272292, 0.36120272631180694], "e": [-2.8036454735982352, 0.4510908150715934], "f": [-2.2031647346026917, 0.3611835941911303], "fʲ": [-2.2799830953986446, 0.3451809256688489], "fː": [-2.6271501013573566, 1.3199588115449246], "i": [-2.572155470813323, 0.540977619119823], "iː": [-2.245678331935848, 0.4944805477945986], "j": [-2.6788766817830783, 0.5353293810670519], "k": [-2.433551637009766, 0.3539595840851239], "kː": [-1.9103138732485216, 0.678185506250247], "l": [-2.6479788184222848, 0.3436700195284161], "lː": [-2.448048595416557, 0.49714553529121974], "m": [-2.530642739057063, 0.35684898566256357], "mʲ": [-2.5479304664047104, 0.3028195830004925], "mʲː": [-2.44285366446762, 0.363422742011348], "n̪": [-2.7051458226855405, 0.3558418883527253], "n̪ː": [-2.134973826775068, 0.3342916163590469], "o": [-2.80248739512024, 0.45795753308498016], "p": [-2.4760819872722846, 0.37485397975068147], "pʲ": [-2.5906185937354453, 0.39260053307153364], "pʲː": [-2.06171531879582, 0.07406659464206233], "sʲ": [-2.2832926697640974, 0.40744435999945716], "sʲː": [-2.1005914529823277, 0.3230865463834678], "s̪": [-2.2671745896605393, 0.3710921841369795], "s̪ː": [-1.891222120193848, 0.345437166597587], "tsʲ": [-2.081020781903387, 0.3351969497410856], "tsʲː": [-1.9919198723485625, 0.3552157249033288], "tʃ": [-2.404339939426889, 0.5240713184588023], "tʃʲ": [-2.1713132364793806, 0.4910820550231237], "tʃʲː": [-1.771285232630738, 0.23908914287702968], "tʃː": [-1.7890658023179222, 0.271412980186127], "tʲ": [-2.466400665214168, 0.4669378873736758], "tʲː": [-1.9623386089498054, 0.5062762186321383], "t̪": [-2.534029310122244, 0.37163802873133006], "t̪s̪": [-2.157585260791186, 0.37100508950354455], "t̪s̪ː": [-1.9182866220674664, 0.25514813511846135], "t̪ː": [-1.8889427095681752, 0.4135169789385847], "u": [-2.489799702756023, 0.4807707528578568], "x": [-2.3363273644567775, 0.4670649668517246], "zʲ": [-2.440827837612538, 0.3769599251634353], "zʲː": [-2.2418003136806477, 0.5404098618423586], "z̪": [-2.46696533163773, 0.356134661380502], "z̪ː": [-2.2027439175397094, 0.5514598746169149], "ç": [-2.24524922780188, 0.5352045918645906], "ɐ": [-2.6846859136150845, 0.5058012028412662], "ɑ": [-2.4784542611614673, 0.4937159070969594], "ɔ": [-2.633464324204635, 0.4709290208788444], "��": [-2.5633372397789254, 0.5003440892887655], "ɟ": [-2.686096564774918, 0.512664169505003], "ɡ": [-2.609909592990076, 0.39551008838134116], "ɦ": [-2.604576009006862, 0.47899189816082866], "ɪ": [-2.672924139547485, 0.5150686831634284], "ɲ": [-2.671392313494225, 0.3921819483449184], "ɲː": [-2.253324477514635, 0.38125447105787424], "ɾ": [-4.533470181964296, 0.42910464556759326], "ɾʲ": [-4.458079990653524, 0.5873413942458783], "ɾʲː": [-4.521145812869596, 0.5286602966199594], "ɾː": [-2.50099406247415, 1.943051046212917], "ʃ": [-2.180191645080337, 0.39868079539226003], "ʃʲ": [-2.0445418824218633, 0.27180431513979225], "ʊ": [-2.658695980541142, 0.5146853486981533], "ʋ": [-2.6891367927666203, 0.421501993252314], "ʋʲ": [-4.550101507617814, 0.365667446491096], "ʋʲː": [-2.7373388210457423, 0.6624305460349353], "ʋː": [-2.088483008790506, 0.41475899183614584], "ʎ": [-4.599987696883298, 0.11082340973115926], "ʎː": [-4.465108150739637, 0.5275195479732839], "ʒ": [-2.5118278760371946, 0.3559801053001986], "ʒʲ": [-2.2917978748276475, 0.3369651507817377], "ʒʲː": [-2.0040306427489187, 0.27699592048407995], "ʝ": [-3.992731437747981, 0.8659053052154354]}}
acoustic/tree CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29d54c30ff565654798c34d3a9877f4d631c22914a60979fe25ba802e5a40a91
3
- size 297349
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dbc392761aba81c521b4920328156fd58b56d543d6e27dce00040080b73dd84
3
+ size 288821
dictionary/ukrainian_mfa.dict CHANGED
The diff for this file is too large to render. See raw diff
 
g2p/ukrainian_mfa/meta.json CHANGED
@@ -1 +1 @@
1
- {"version": "3.2.0", "architecture": "phonetisaurus", "train_date": "2026-05-29 17:35:18.829984", "phones": ["\u025f", "\u0272\u02d0", "i\u02d0", "j", "\u027e\u02b2", "s\u032a", "s\u032a\u02d0", "\u0292\u02b2", "\u0272", "\u025b", "ts\u02b2\u02d0", "\u028b\u02d0", "d\u02b2", "n\u032a\u02d0", "\u028b", "e", "\u028b\u02b2", "\u028e", "p", "m\u02b2", "\u0254", "d\u032a\u02d0", "d\u032az\u032a", "k\u02d0", "b\u02b2\u02d0", "t\u032as\u032a", "d\u02b2\u02d0", "u", "z\u02b2\u02d0", "\u0261\u02d0", "p\u02b2\u02d0", "t\u0283", "m\u02b2\u02d0", "\u0283\u02b2\u02d0", "t\u0283\u02b2\u02d0", "l", "f", "o", "l\u02d0", "b", "\u0266\u02d0", "\u0250", "s\u02b2", "ts\u02b2", "\u0261", "\u027e\u02d0", "t\u032a", "\u0266", "t\u032a\u02d0", "\u029d", "x", "\u028a", "\u0251", "d\u032az\u032a\u02d0", "f\u02d0", "n\u032a", "f\u02b2", "k", "\u0283", "s\u02b2\u02d0", "i", "\u0283\u02b2", "\u0292\u02b2\u02d0", "t\u0283\u02b2", "d\u032a", "z\u02b2", "t\u02b2\u02d0", "b\u02b2", "z\u032a", "\u00e7", "\u026a", "p\u02b2", "\u028e\u02d0", "t\u0283\u02d0", "c\u02d0", "z\u032a\u02d0", "m", "\u028b\u02b2\u02d0", "d\u0292", "c", "\u027e", "\u027e\u02b2\u02d0", "\u0292", "t\u032as\u032a\u02d0", "dz\u02b2", "t\u02b2", "b\u02d0"], "graphemes": ["\u0442", "\u043d", "\u043a", "\u0446", "\u0435", "\u0445", "\u0457", "\u0431", "\u044e", "\u0449", "\u0444", "\u0436", "\u0447", "\u043b", "\u043f", "\u0491", "\u0443", "\u0437", "\u0456", "\u0433", "\u0434", "'", "\u0430", "\u0440", "\u044f", "\u0441", "\u043c", "\u0432", "\u044c", "\u0448", "\u0439", "\u043e", "\u0438", "\u0454"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": false, "evaluation": {"num_words": 6496, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 58467, "num_graphemes": 34, "num_phones": 87}}
 
1
+ {"version": "3.2.0", "architecture": "phonetisaurus", "train_date": "2026-05-29 17:35:18.829984", "phones": ["\u0261", "d\u0292", "t\u0283", "ts\u02b2\u02d0", "k", "e", "\u028e", "\u027e\u02b2\u02d0", "t\u032a\u02d0", "\u028e\u02d0", "\u028b\u02b2", "z\u032a", "u", "z\u032a\u02d0", "o", "n\u032a\u02d0", "b\u02d0", "b\u02b2", "\u0292\u02b2\u02d0", "\u0251", "\u0266\u02d0", "\u025f", "d\u032a", "\u0272\u02d0", "c\u02d0", "l\u02d0", "t\u02b2\u02d0", "ts\u02b2", "j", "s\u02b2\u02d0", "t\u0283\u02d0", "m\u02b2\u02d0", "c", "t\u032a", "\u0272", "\u028b", "b", "f\u02d0", "\u0250", "\u0292", "k\u02d0", "z\u02b2\u02d0", "m", "\u00e7", "n\u032a", "p", "s\u032a\u02d0", "d\u032az\u032a", "t\u02b2", "dz\u02b2", "\u027e\u02d0", "f", "\u028a", "p\u02b2\u02d0", "\u0283", "\u0254", "t\u032as\u032a\u02d0", "m\u02b2", "t\u0283\u02b2", "t\u032as\u032a", "\u025b", "d\u02b2\u02d0", "p\u02b2", "x", "d\u02b2", "\u027e", "i\u02d0", "\u028b\u02b2\u02d0", "\u0283\u02b2\u02d0", "i", "\u0292\u02b2", "\u0261\u02d0", "f\u02b2", "d\u032a\u02d0", "\u027e\u02b2", "s\u032a", "\u026a", "\u0283\u02b2", "\u0266", "\u029d", "z\u02b2", "l", "d\u032az\u032a\u02d0", "b\u02b2\u02d0", "\u028b\u02d0", "s\u02b2", "t\u0283\u02b2\u02d0"], "graphemes": ["\u0454", "\u0437", "\u0447", "\u0456", "\u0444", "\u044c", "\u0446", "\u043a", "\u0430", "\u044e", "\u0491", "\u0443", "\u043b", "\u0448", "\u0438", "\u043e", "'", "\u0435", "\u043c", "\u0442", "\u0445", "\u0449", "\u044f", "\u0440", "\u043d", "\u043f", "\u0439", "\u0441", "\u0457", "\u0434", "\u0436", "\u0433", "\u0431", "\u0432"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": false, "evaluation": {"num_words": 6496, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 58467, "num_graphemes": 34, "num_phones": 87}}