Instructions to use MontrealCorpusTools/ukrainian_mfa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Montreal Forced Aligner
How to use MontrealCorpusTools/ukrainian_mfa with Montreal Forced Aligner:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Upload folder using huggingface_hub
Browse files- README.md +3 -7
- acoustic/final.alimdl +2 -2
- acoustic/final.mdl +2 -2
- acoustic/lda.mat +0 -0
- acoustic/meta.json +1 -1
- acoustic/tree +2 -2
- dictionary/ukrainian_mfa.dict +0 -0
- g2p/ukrainian_mfa/meta.json +1 -1
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:**
|
| 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,
|
| 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,
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 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.
|
|
|
|
| 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:
|
| 3 |
-
size
|
|
|
|
| 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": ["\
|
|
|
|
| 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}}
|