Instructions to use MontrealCorpusTools/mandarin_mfa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Montreal Forced Aligner
How to use MontrealCorpusTools/mandarin_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 +2 -2
- 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/mandarin_china_mfa.dict +0 -0
- dictionary/mandarin_taiwan_mfa.dict +0 -0
- dictionary/rules.yaml +98 -98
- g2p/mandarin_china_mfa/meta.json +1 -1
- g2p/mandarin_taiwan_mfa/meta.json +1 -1
README.md
CHANGED
|
@@ -116,9 +116,9 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
|
|
| 116 |
|
| 117 |
##### Diphthongs
|
| 118 |
* aw
|
|
|
|
| 119 |
* aj
|
| 120 |
* ej
|
| 121 |
-
* ow
|
| 122 |
|
| 123 |
|
| 124 |
#### Details for mandarin_china_mfa dictionary and G2P model
|
|
@@ -164,10 +164,10 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
|
|
| 164 |
| **Open** | | | a | | |
|
| 165 |
|
| 166 |
##### Diphthongs
|
|
|
|
| 167 |
* aw
|
| 168 |
* aj
|
| 169 |
* ej
|
| 170 |
-
* ow
|
| 171 |
|
| 172 |
|
| 173 |
## Training Details
|
|
|
|
| 116 |
|
| 117 |
##### Diphthongs
|
| 118 |
* aw
|
| 119 |
+
* ow
|
| 120 |
* aj
|
| 121 |
* ej
|
|
|
|
| 122 |
|
| 123 |
|
| 124 |
#### Details for mandarin_china_mfa dictionary and G2P model
|
|
|
|
| 164 |
| **Open** | | | a | | |
|
| 165 |
|
| 166 |
##### Diphthongs
|
| 167 |
+
* ow
|
| 168 |
* aw
|
| 169 |
* aj
|
| 170 |
* ej
|
|
|
|
| 171 |
|
| 172 |
|
| 173 |
## Training Details
|
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:d99010c7785a0aff457ac842c905a0a779ab12d62b5cc168080e337f6d192337
|
| 3 |
+
size 50594436
|
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 sha256:121c1256afc4c81cf927f4b789358849cfa23e8ee6518876844e5ce75fba53c9
|
| 3 |
+
size 50594436
|
acoustic/lda.mat
CHANGED
|
Binary files a/acoustic/lda.mat and b/acoustic/lda.mat differ
|
|
|
acoustic/meta.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"phones": ["a", "aj", "aj˥", "aj˥˩", "aj˧", "aj˧˥", "aj˨˩˦", "aj˩", "aw", "aw˥", "aw˥˩", "aw˧", "aw˧˥", "aw˨˩˦", "aw˩", "a˥", "a˥˩", "a˧", "a˧˥", "a˨˩˦", "a˩", "e", "ej", "ej˥", "ej˥˩", "ej˧", "ej˧˥", "ej˨˩˦", "ej˩", "e˥", "e˥˩", "e˧", "e˧˥", "e˨˩˦", "e˩", "f", "i", "i˥", "i˥˩", "i˧", "i˧˥", "i˨˩˦", "i˩", "j", "k", "kʰ", "kʷ", "l", "m", "mʲ", "m̩", "m̩˥", "m̩˥˩", "m̩˧", "m̩˧˥", "m̩˨˩˦", "n", "n̩˥˩", "n̩˧˥", "n̩˨˩˦", "o", "ow", "ow˥", "ow˥˩", "ow˧", "ow˧˥", "ow˨˩˦", "ow˩", "o˥", "o˥˩", "o˧", "o˧˥", "o˨˩˦", "o˩", "p", "pʰ", "pʲ", "pʷ", "s", "t", "ts", "tsʰ", "tɕ", "tɕʰ", "tɕʷ", "tʰ", "tʲ", "tʷ", "u", "u˥", "u˥˩", "u˧", "u˧˥", "u˨˩˦", "u˩", "w", "x", "xʷ", "y", "y˥", "y˥˩", "y˧", "y˧˥", "y˨˩˦", "y˩", "z̩", "z̩˥", "z̩˥˩", "z̩˧", "z̩˧˥", "z̩˨˩˦", "z̩˩", "ŋ", "ŋ̍", "ŋ̍˥˩", "ŋ̍˧˥", "ŋ̍˨˩˦", "ɕ", "ɕʷ", "ə", "ə˥", "ə˥˩", "ə˧", "ə˧˥", "ə˨˩˦", "ə˩", "ɥ", "ɲ", "ɻ", "ʂ", "ʈʂ", "ʈʂʰ", "ʎ", "ʐ", "ʐ̩", "ʐ̩˥", "ʐ̩˥˩", "ʐ̩˧", "ʐ̩˧˥", "ʐ̩˨˩˦", "ʐ̩˩", "ʔ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "aj": 4, "aj˥": 5, "aj˥˩": 6, "aj˧": 7, "aj˧˥": 8, "aj˨˩˦": 9, "aj˩": 10, "aw": 11, "aw˥": 12, "aw˥˩": 13, "aw˧": 14, "aw˧˥": 15, "aw˨˩˦": 16, "aw˩": 17, "a˥": 18, "a˥˩": 19, "a˧": 20, "a˧˥": 21, "a˨˩˦": 22, "a˩": 23, "e": 24, "ej": 25, "ej˥": 26, "ej˥˩": 27, "ej˧": 28, "ej˧˥": 29, "ej˨˩˦": 30, "ej˩": 31, "e˥": 32, "e˥˩": 33, "e˧": 34, "e˧˥": 35, "e˨˩˦": 36, "e˩": 37, "f": 38, "i": 39, "i˥": 40, "i˥˩": 41, "i˧": 42, "i˧˥": 43, "i˨˩˦": 44, "i˩": 45, "j": 46, "k": 47, "kʰ": 48, "kʷ": 49, "l": 50, "m": 51, "mʲ": 52, "m̩": 53, "m̩˥": 54, "m̩˥˩": 55, "m̩˧": 56, "m̩˧˥": 57, "m̩˨˩˦": 58, "n": 59, "n̩˥˩": 60, "n̩˧˥": 61, "n̩˨˩˦": 62, "o": 63, "ow": 64, "ow˥": 65, "ow˥˩": 66, "ow˧": 67, "ow˧˥": 68, "ow˨˩˦": 69, "ow˩": 70, "o˥": 71, "o˥˩": 72, "o˧": 73, "o˧˥": 74, "o˨˩˦": 75, "o˩": 76, "p": 77, "pʰ": 78, "pʲ": 79, "pʷ": 80, "s": 81, "t": 82, "ts": 83, "tsʰ": 84, "tɕ": 85, "tɕʰ": 86, "tɕʷ": 87, "tʰ": 88, "tʲ": 89, "tʷ": 90, "u": 91, "u˥": 92, "u˥˩": 93, "u˧": 94, "u˧˥": 95, "u˨˩˦": 96, "u˩": 97, "w": 98, "x": 99, "xʷ": 100, "y": 101, "y˥": 102, "y˥˩": 103, "y˧": 104, "y˧˥": 105, "y˨˩˦": 106, "y˩": 107, "z̩": 108, "z̩˥": 109, "z̩˥˩": 110, "z̩˧": 111, "z̩˧˥": 112, "z̩˨˩˦": 113, "z̩˩": 114, "ŋ": 115, "ŋ̍": 116, "ŋ̍˥˩": 117, "ŋ̍˧˥": 118, "ŋ̍˨˩˦": 119, "ɕ": 120, "ɕʷ": 121, "ə": 122, "ə˥": 123, "ə˥˩": 124, "ə˧": 125, "ə˧˥": 126, "ə˨˩˦": 127, "ə˩": 128, "ɥ": 129, "ɲ": 130, "ɻ": 131, "ʂ": 132, "ʈʂ": 133, "ʈʂʰ": 134, "ʎ": 135, "ʐ": 136, "ʐ̩": 137, "ʐ̩˥": 138, "ʐ̩˥˩": 139, "ʐ̩˧": 140, "ʐ̩˧˥": 141, "ʐ̩˨˩˦": 142, "ʐ̩˩": 143, "ʔ": 144}, "phone_groups": {"0": ["f"], "1": ["aj", "aj˥", "aj˥˩", "aj˧", "aj˧˥", "aj˨˩˦", "aj˩"], "2": ["aw", "aw˥", "aw˥˩", "aw˧", "aw˧˥", "aw˨˩˦", "aw˩"], "3": ["a", "a˥", "a˥˩", "a˧", "a˧˥", "a˨˩˦", "a˩"], "4": ["ej", "ej˥", "ej˥˩", "ej˧", "ej˧˥", "ej˨˩˦", "ej˩"], "5": ["e", "e˥", "e˥˩", "e˧", "e˧˥", "e˨˩˦", "e˩"], "6": ["i", "i˥", "i˥˩", "i˧", "i˧˥", "i˨˩˦", "i˩", "j"], "7": ["k"], "8": ["kʰ", "kʷ"], "9": ["l", "ʎ"], "10": ["m", "mʲ", "m̩", "m̩˥", "m̩˥˩", "m̩˧", "m̩˧˥", "m̩˨˩˦"], "11": ["n", "n̩˥˩", "n̩˧˥", "n̩˨˩˦", "ɲ"], "12": ["ow", "ow˥", "ow˥˩", "ow˧", "ow˧˥", "ow˨˩˦", "ow˩"], "13": ["o", "o˥", "o˥˩", "o˧", "o˧˥", "o˨˩˦", "o˩"], "14": ["p"], "15": ["pʰ", "pʲ", "pʷ"], "16": ["s"], "17": ["t"], "18": ["ts"], "19": ["tsʰ"], "20": ["tʰ", "tʲ", "tʷ"], "21": ["u", "u˥", "u˥˩", "u˧", "u˧˥", "u˨˩˦", "u˩", "w"], "22": ["x", "xʷ"], "23": ["y", "y˥", "y˥˩", "y˧", "y˧˥", "y˨˩˦", "y˩", "ɥ"], "24": ["z̩", "z̩˥", "z̩˥˩", "z̩˧", "z̩˧˥", "z̩˨˩˦", "z̩˩"], "25": ["ŋ", "ŋ̍", "ŋ̍˥˩", "ŋ̍˧˥", "ŋ̍˨˩˦"], "26": ["ə", "ə˥", "ə˥˩", "ə˧", "ə˧˥", "ə˨˩˦", "ə˩"], "27": [], "28": ["ɕ", "ɕʷ", "ʂ"], "29": ["tɕ", "ʈʂ"], "30": ["tɕʰ", "tɕʷ", "ʈʂʰ"], "31": ["ɻ"], "32": ["ʐ", "ʐ̩", "ʐ̩˥", "ʐ̩˥˩", "ʐ̩˧", "ʐ̩˧˥", "ʐ̩˨˩˦", "ʐ̩˩"], "33": ["ʔ"]}, "version": "3.3.0", "architecture": "gmm-hmm", "train_date": "2026-06-11 17:28:13.943464", "training": {"audio_duration": 2643393.042393958, "num_speakers": 7272, "num_utterances": 635145, "num_oovs": 0, "average_log_likelihood": -50.458497490932714}, "dictionaries": {"names": ["mandarin_china_mfa", "mandarin_taiwan_mfa"], "default": "mandarin_china_mfa", "silence_word": "<eps>", "oov_word": "<unk>", "bracketed_word": "[bracketed]", "laughter_word": "[laughter]", "clitic_marker": "'", "position_dependent_phones": false}, "language": "chinese", "tokenization": "zh", "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": true, "use_voicing": true, "min_f0": 50, "max_f0": 800, "delta_pitch": 0.005, "penalty_factor": 0.1, "silence_weight": 0.0, "splice_left_context": 3, "splice_right_context": 3}, "oov_phone": "spn", "optional_silence_phone": "sil", "phone_set_type": "UNKNOWN", "silence_probability": 0.2, "initial_silence_probability": 0.2, "final_silence_correction": 0.99, "final_non_silence_correction": 0.030000000000000002, "duration_information": {"aw˧": [0.09833330909411113, 0.040188899010180294], "e": [0.05666669209798177, 0.015275185721770784], "n̩˨˩˦": [0.013333360354105631, 0.005773462773404995], "y": [0.039999961853027344, 0.04242602923543019], "y˥": [0.10753112060139478, 0.06633079662675737], "y˥˩": [0.12044553470584932, 0.06954867359161486], "y˧˥": [0.1521650714942236, 0.08690065527560001], "y˨˩˦": [0.12777634114718675, 0.07236732362029771], "z̩˥": [0.10707732068908493, 0.06338322114546288], "z̩˥˩": [0.0961825639180125, 0.05112998968486207], "z̩˧": [0.09965765556554697, 0.06094161053676058], "z̩˧˥": [0.1126421779262006, 0.06553586141594285], "z̩˨˩˦": [0.09678123249057538, 0.0566201341427446], "z̩˩": [0.08690746880957137, 0.053290551250414514], "ŋ": [0.08819470476065501, 0.046615515065164044], "ɕ": [0.11901830637596723, 0.045778593181008076], "ɕʷ": [0.11802584534921463, 0.042693764055051125], "ə": [0.09091536940693622, 0.052488245422996266], "ə˥": [0.06439586890336653, 0.034959321669488716], "ə˥˩": [0.06677743062115488, 0.035873870300183894], "ə˧": [0.08404358420042957, 0.05099692040783799], "ə˧˥": [0.06640109434106103, 0.038648188197492946], "ə˨˩˦": [0.050535720405291404, 0.026298129459328703], "ə˩": [0.07202564595474004, 0.040634376436879636], "ɥ": [0.07917002608201401, 0.037417168440248665], "ɲ": [0.07823062455203164, 0.03405834836831032], "ɻ": [0.09587972447649064, 0.0457341445038691], "ʂ": [0.11796884531085698, 0.04546370021833372], "ʈʂ": [0.08346012217337465, 0.033310464425265356], "ʈʂʰ": [0.1121910947544673, 0.03812218917510983], "ʎ": [0.023530121443271445, 0.0372901996168465], "ʐ": [0.08085267629086722, 0.03711347533154361], "ʐ̩": [0.020458891617408447, 0.007642622913471767], "ʐ̩˥": [0.0907782242655954, 0.05583438268992173], "ʐ̩˥˩": [0.10729945058853818, 0.06615380762527384], "ʐ̩˧": [0.055999996987256134, 0.03808373183664602], "ʐ̩˧˥": [0.0860592624457871, 0.05716138757751209], "ʐ̩˨˩˦": [0.08477033006394262, 0.05111062227693928], "ʐ̩˩": [0.074897050813717, 0.04976517365431854], "ʔ": [0.07547436112151641, 0.04082705139581845], "y˩": [0.12285709381103516, 0.06848708126648126], "z̩": [0.04533332188924154, 0.01884776050799601], "a˥˩": [0.09926087449246379, 0.04788594730996235], "a˧": [0.08911870060850391, 0.050344189791030114], "a˧˥": [0.09896388197371386, 0.05158448422971394], "a˨˩˦": [0.08754037846327493, 0.043462809651193424], "a˩": [0.11782521766725843, 0.05766373460195309], "ej": [0.16058480238531067, 0.06512525984538682], "ej˥": [0.10785704689836108, 0.055106278380678546], "ej˥˩": [0.10704651155296936, 0.055750056010441695], "ej˧˥": [0.11448496224220181, 0.06294880281795569], "ej˨˩˦": [0.10226295670893996, 0.04771525590326557], "ej˩": [0.12924051511136792, 0.07119443598994915], "e˥": [0.08666066251122198, 0.046010436377643044], "e˥˩": [0.0837381859702178, 0.04516035963383656], "e˧": [0.07318177006461403, 0.03137880746613511], "e˧˥": [0.0893712204031966, 0.04961665223887116], "e˨˩˦": [0.07424534082146879, 0.03916458000438377], "e˩": [0.09546746925444592, 0.04496283032812067], "f": [0.10814251885570723, 0.04817047280167293], "i": [0.1946602013432285, 0.07206976826010891], "i˥": [0.09991115714098701, 0.06193568954205623], "i˥˩": [0.1112831397517615, 0.06507339160217562], "i˧": [0.08985294664607328, 0.04345155784679993], "i˧˥": [0.09151274363471319, 0.057475182276164105], "i˨˩˦": [0.09884277644939551, 0.06094097931054765], "n̩˥˩": [0.014285707314099585, 0.011338920443236651], "a": [0.18458129888629907, 0.09421362463283765], "aj˥": [0.12047115197129747, 0.04946377349155198], "aj˥˩": [0.1254964319657768, 0.053771842559275015], "aj˧˥": [0.12007174327070007, 0.057932534429106806], "aj˨˩˦": [0.1195332565552317, 0.04417214093438846], "aj˩": [0.12056307655733985, 0.05653178850852299], "aw˥": [0.13401777683873517, 0.05020853156042797], "aw˥˩": [0.12885518960583947, 0.05413164494552235], "aw˧˥": [0.1270646449383, 0.057586564810876165], "aw˨˩˦": [0.11191864343908335, 0.04519766975769665], "aw˩": [0.13558384378751118, 0.046358906572064644], "a˥": [0.09897147052915554, 0.05090218962946023], "i˩": [0.10831800567377232, 0.07022405971484143], "j": [0.06859648643586078, 0.031089136637824206], "k": [0.07407715905035078, 0.03211010955777015], "kʰ": [0.11470007257970388, 0.04452491375508201], "kʷ": [0.08163751459949169, 0.03825699090581018], "l": [0.06511819587111528, 0.03424860849469076], "m": [0.07770057434769281, 0.03187881825738688], "mʲ": [0.07708265582890929, 0.027536880545817006], "m̩˧": [0.11351850849610788, 0.04949393887829205], "n": [0.07753274926127032, 0.04297621047309884], "o": [0.01000004510084788, 1.5840151626968275e-07], "ow": [0.15684469386631555, 0.09378856668479686], "ow˥": [0.12238927599281481, 0.0553632998414608], "ow˥˩": [0.1101293896538982, 0.05575180217470729], "ow˧": [0.11743119855721791, 0.06319824542871083], "ow˧˥": [0.11964212634244975, 0.05517249669196917], "ow˨˩˦": [0.10256147624771468, 0.04585507536806213], "ow˩": [0.11409324716409872, 0.06222149164815993], "o˥": [0.0858400315359253, 0.05434072102988911], "o˥˩": [0.09226506206549796, 0.051266740619833745], "o˧": [0.067192508336057, 0.0519886589721553], "o˧˥": [0.08322918232586435, 0.052109928534976604], "o˨˩˦": [0.06319149225802732, 0.06562710488844534], "o˩": [0.07154340376041327, 0.054193775676728825], "p": [0.0762198810656691, 0.033527264729761044], "pʰ": [0.10483437088972748, 0.04724232620838715], "pʲ": [0.08958614165176602, 0.043647185355748006], "pʷ": [0.07730061146016208, 0.038161283910668364], "s": [0.1305177058448928, 0.05410650742660087], "t": [0.06244461101701923, 0.034296463936500377], "ts": [0.08722162298688886, 0.035733220745720856], "tsʰ": [0.12682007515052865, 0.046084912780226514], "tɕ": [0.09507191375537702, 0.035408749069653654], "tɕʰ": [0.13650172667731492, 0.0487872538623162], "tɕʷ": [0.10687843610223895, 0.038333658789992765], "tʰ": [0.1017273496052441, 0.04154904251603982], "tʲ": [0.08621475703348491, 0.04490564530958987], "tʷ": [0.08001692556335746, 0.03993364074748392], "u˥": [0.07632670042535596, 0.04752295705589983], "u˥˩": [0.09780727238552925, 0.0594930785271066], "u˧": [0.06680146276074297, 0.05057299554098824], "u˧˥": [0.09293159802205544, 0.058813275398930456], "u˨˩˦": [0.10594457310002092, 0.06291266330450009], "u˩": [0.0884401391291637, 0.05899232038858452], "w": [0.0711566033953967, 0.034710414846703896], "x": [0.10446516494399515, 0.0447792472332621], "xʷ": [0.10457423429601709, 0.04347768861969501]}}
|
|
|
|
| 1 |
+
{"phones": ["a", "aj", "aj˥", "aj˥˩", "aj˧", "aj˧˥", "aj˨˩˦", "aj˩", "aw", "aw˥", "aw˥˩", "aw˧", "aw˧˥", "aw˨˩˦", "aw˩", "a˥", "a˥˩", "a˧", "a˧˥", "a˨˩˦", "a˩", "e", "ej", "ej˥", "ej˥˩", "ej˧", "ej˧˥", "ej˨˩˦", "ej˩", "e˥", "e˥˩", "e˧", "e˧˥", "e˨˩˦", "e˩", "f", "i", "i˥", "i˥˩", "i˧", "i˧˥", "i˨˩˦", "i˩", "j", "k", "kʰ", "kʷ", "l", "m", "mʲ", "m̩", "m̩˥", "m̩˥˩", "m̩˧", "m̩˧˥", "m̩˨˩˦", "n", "n̩˥˩", "n̩˧˥", "n̩˨˩˦", "o", "ow", "ow˥", "ow˥˩", "ow˧", "ow˧˥", "ow˨˩˦", "ow˩", "o˥", "o˥˩", "o˧", "o˧˥", "o˨˩˦", "o˩", "p", "pʰ", "pʲ", "pʷ", "s", "t", "ts", "tsʰ", "tɕ", "tɕʰ", "tɕʷ", "tʰ", "tʲ", "tʷ", "u", "u˥", "u˥˩", "u˧", "u˧˥", "u˨˩˦", "u˩", "w", "x", "xʷ", "y", "y˥", "y˥˩", "y˧", "y˧˥", "y˨˩˦", "y˩", "z̩", "z̩˥", "z̩˥˩", "z̩˧", "z̩˧˥", "z̩˨˩˦", "z̩˩", "ŋ", "ŋ̍", "ŋ̍˥˩", "ŋ̍˧˥", "ŋ̍˨˩˦", "ɕ", "ɕʷ", "ə", "ə˥", "ə˥˩", "ə˧", "ə˧˥", "ə˨˩˦", "ə˩", "ɥ", "ɲ", "ɻ", "ʂ", "ʈʂ", "ʈʂʰ", "ʎ", "ʐ", "ʐ̩", "ʐ̩˥", "ʐ̩˥˩", "ʐ̩˧", "ʐ̩˧˥", "ʐ̩˨˩˦", "ʐ̩˩", "ʔ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "aj": 4, "aj˥": 5, "aj˥˩": 6, "aj˧": 7, "aj˧˥": 8, "aj˨˩˦": 9, "aj˩": 10, "aw": 11, "aw˥": 12, "aw˥˩": 13, "aw˧": 14, "aw˧˥": 15, "aw˨˩˦": 16, "aw˩": 17, "a˥": 18, "a˥˩": 19, "a˧": 20, "a˧˥": 21, "a˨˩˦": 22, "a˩": 23, "e": 24, "ej": 25, "ej˥": 26, "ej˥˩": 27, "ej˧": 28, "ej˧˥": 29, "ej˨˩˦": 30, "ej˩": 31, "e˥": 32, "e˥˩": 33, "e˧": 34, "e˧˥": 35, "e˨˩˦": 36, "e˩": 37, "f": 38, "i": 39, "i˥": 40, "i˥˩": 41, "i˧": 42, "i˧˥": 43, "i˨˩˦": 44, "i˩": 45, "j": 46, "k": 47, "kʰ": 48, "kʷ": 49, "l": 50, "m": 51, "mʲ": 52, "m̩": 53, "m̩˥": 54, "m̩˥˩": 55, "m̩˧": 56, "m̩˧˥": 57, "m̩˨˩˦": 58, "n": 59, "n̩˥˩": 60, "n̩˧˥": 61, "n̩˨˩˦": 62, "o": 63, "ow": 64, "ow˥": 65, "ow˥˩": 66, "ow˧": 67, "ow˧˥": 68, "ow˨˩˦": 69, "ow˩": 70, "o˥": 71, "o˥˩": 72, "o˧": 73, "o˧˥": 74, "o˨˩˦": 75, "o˩": 76, "p": 77, "pʰ": 78, "pʲ": 79, "pʷ": 80, "s": 81, "t": 82, "ts": 83, "tsʰ": 84, "tɕ": 85, "tɕʰ": 86, "tɕʷ": 87, "tʰ": 88, "tʲ": 89, "tʷ": 90, "u": 91, "u˥": 92, "u˥˩": 93, "u˧": 94, "u˧˥": 95, "u˨˩˦": 96, "u˩": 97, "w": 98, "x": 99, "xʷ": 100, "y": 101, "y˥": 102, "y˥˩": 103, "y˧": 104, "y˧˥": 105, "y˨˩˦": 106, "y˩": 107, "z̩": 108, "z̩˥": 109, "z̩˥˩": 110, "z̩˧": 111, "z̩˧˥": 112, "z̩˨˩˦": 113, "z̩˩": 114, "ŋ": 115, "ŋ̍": 116, "ŋ̍˥˩": 117, "ŋ̍˧˥": 118, "ŋ̍˨˩˦": 119, "ɕ": 120, "ɕʷ": 121, "ə": 122, "ə˥": 123, "ə˥˩": 124, "ə˧": 125, "ə˧˥": 126, "ə˨˩˦": 127, "ə˩": 128, "ɥ": 129, "ɲ": 130, "ɻ": 131, "ʂ": 132, "ʈʂ": 133, "ʈʂʰ": 134, "ʎ": 135, "ʐ": 136, "ʐ̩": 137, "ʐ̩˥": 138, "ʐ̩˥˩": 139, "ʐ̩˧": 140, "ʐ̩˧˥": 141, "ʐ̩˨˩˦": 142, "ʐ̩˩": 143, "ʔ": 144}, "phone_groups": {"0": ["f"], "1": ["aj", "aj˥", "aj˥˩", "aj˧", "aj˧˥", "aj˨˩˦", "aj˩"], "2": ["aw", "aw˥", "aw˥˩", "aw˧", "aw˧˥", "aw˨˩˦", "aw˩"], "3": ["a", "a˥", "a˥˩", "a˧", "a˧˥", "a˨˩˦", "a˩"], "4": ["ej", "ej˥", "ej˥˩", "ej˧", "ej˧˥", "ej˨˩˦", "ej˩"], "5": ["e", "e˥", "e˥˩", "e˧", "e˧˥", "e˨˩˦", "e˩"], "6": ["i", "i˥", "i˥˩", "i˧", "i˧˥", "i˨˩˦", "i˩", "j"], "7": ["k"], "8": ["kʰ", "kʷ"], "9": ["l", "ʎ"], "10": ["m", "mʲ", "m̩", "m̩˥", "m̩˥˩", "m̩˧", "m̩˧˥", "m̩˨˩˦"], "11": ["n", "n̩˥˩", "n̩˧˥", "n̩˨˩˦", "ɲ"], "12": ["ow", "ow˥", "ow˥˩", "ow˧", "ow˧˥", "ow˨˩˦", "ow˩"], "13": ["o", "o˥", "o˥˩", "o˧", "o˧˥", "o˨˩˦", "o˩"], "14": ["p"], "15": ["pʰ", "pʲ", "pʷ"], "16": ["s"], "17": ["t"], "18": ["ts"], "19": ["tsʰ"], "20": ["tʰ", "tʲ", "tʷ"], "21": ["u", "u˥", "u˥˩", "u˧", "u˧˥", "u˨˩˦", "u˩", "w"], "22": ["x", "xʷ"], "23": ["y", "y˥", "y˥˩", "y˧", "y˧˥", "y˨˩˦", "y˩", "ɥ"], "24": ["z̩", "z̩˥", "z̩˥˩", "z̩˧", "z̩˧˥", "z̩˨˩˦", "z̩˩"], "25": ["ŋ", "ŋ̍", "ŋ̍˥˩", "ŋ̍˧˥", "ŋ̍˨˩˦"], "26": ["ə", "ə˥", "ə˥˩", "ə˧", "ə˧˥", "ə˨˩˦", "ə˩"], "27": [], "28": ["ɕ", "ɕʷ", "ʂ"], "29": ["tɕ", "ʈʂ"], "30": ["tɕʰ", "tɕʷ", "ʈʂʰ"], "31": ["ɻ"], "32": ["ʐ", "ʐ̩", "ʐ̩˥", "ʐ̩˥˩", "ʐ̩˧", "ʐ̩˧˥", "ʐ̩˨˩˦", "ʐ̩˩"], "33": ["ʔ"]}, "version": "3.4.3", "architecture": "gmm-hmm", "train_date": "2026-10-14 09:39:47.506183", "training": {"audio_duration": 2643826.5339878458, "num_speakers": 7272, "num_utterances": 635161, "num_oovs": 0, "average_log_likelihood": -50.66456339267323}, "dictionaries": {"names": ["mandarin_china_mfa", "mandarin_taiwan_mfa"], "default": "mandarin_china_mfa", "silence_word": "<eps>", "oov_word": "<unk>", "bracketed_word": "[bracketed]", "laughter_word": "[laughter]", "clitic_marker": "'", "position_dependent_phones": false}, "language": "chinese", "tokenization": "zh", "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": true, "use_voicing": true, "min_f0": 50, "max_f0": 800, "delta_pitch": 0.005, "penalty_factor": 0.1, "silence_weight": 0.0, "splice_left_context": 3, "splice_right_context": 3}, "oov_phone": "spn", "optional_silence_phone": "sil", "phone_set_type": "UNKNOWN", "silence_probability": 0.2, "initial_silence_probability": 0.2, "final_silence_correction": 0.99, "final_non_silence_correction": 0.030000000000000002, "duration_information": {"aj˥˩": [-2.1955978869276223, 0.44318880739851546], "aw˨˩˦": [-2.257955089133259, 0.40585095189252113], "a˥˩": [-2.4342872827043993, 0.4889546761021809], "a˧": [-2.642096030184177, 0.5428231811732654], "a˧˥": [-2.4444292237999545, 0.522406280852663], "a˨˩˦": [-2.581278802892365, 0.4926196758861528], "a˩": [-2.380378217455862, 0.5245986416416261], "e": [-2.762721848918983, 0.45920124601961604], "i": [-2.9124617819943994, 1.0520016690707124], "i˥": [-2.4865205170200837, 0.5721389442519448], "i˥˩": [-2.36149094502131, 0.5492999419764772], "i˧˥": [-2.5700178391807826, 0.5493094048081848], "i˨˩˦": [-2.502484576950997, 0.5722030730326224], "i˩": [-2.6891463696429, 0.6433714204825092], "j": [-2.756996462879792, 0.42040935923521855], "k": [-2.6610336157902843, 0.4057929236716045], "n̩˥˩": [-4.605168289841705, 7.39026181430843e-06], "o": [-1.6426367147978507, 0.5504979677746732], "ow": [-2.0397562637278535, 0.610088389070018], "ow˥": [-2.2003756270073147, 0.44090491278356525], "ow˥˩": [-2.323903479205177, 0.4829999489416604], "ow˧": [-2.314874667519803, 0.6299392950308252], "ow˧˥": [-2.1998960394936704, 0.43516641255389565], "ow˨˩˦": [-2.345379329203695, 0.4335940772926663], "ow˩": [-2.287124378079845, 0.5408017935272733], "o˥": [-2.6272594746722957, 0.538857243713718], "o˥˩": [-2.54383714996885, 0.5221576745675489], "o˧": [-3.013613541654291, 0.6836275645087581], "o˧˥": [-2.6735692356833782, 0.5242618398803852], "o˨˩˦": [-3.0443130073730797, 0.6536658504659876], "o˩": [-2.9790269309319286, 0.8542453160910617], "p": [-2.633260896195403, 0.39060949586699223], "pʰ": [-2.3120640170645665, 0.42120541137460715], "pʲ": [-2.5114585110379104, 0.4812879008111998], "pʷ": [-2.6501778168910834, 0.46320504303896604], "s": [-2.101272657663437, 0.3716826999038819], "t": [-2.833913524127057, 0.3731752752926771], "ts": [-2.4836461098453038, 0.3876271872764924], "tsʰ": [-2.1160245590924704, 0.3834957109078589], "tɕ": [-2.395622341591377, 0.3592544291697464], "tɕʰ": [-2.049572513596601, 0.36273100667532976], "tɕʷ": [-2.309649919209912, 0.3816202657980774], "tʰ": [-2.375566641758384, 0.42150390269533583], "tʲ": [-2.5701177798956865, 0.49929554561782225], "tʷ": [-2.5967570159836897, 0.46042824274354544], "u˥": [-2.677742445693881, 0.479747752879436], "u˥˩": [-2.5016927969227156, 0.5481372854184161], "u˧": [-2.9561152895531477, 0.7652069828196997], "u˧˥": [-2.532607523627718, 0.5594606877521243], "u˨˩˦": [-2.381214987691281, 0.553710813205882], "u˩": [-2.788791183503871, 0.6289864792445844], "w": [-2.685230378765297, 0.4442049433980681], "x": [-2.324329299519838, 0.46023269680492623], "xʷ": [-2.330370405187556, 0.4368646421854322], "y˥": [-2.4077960946227415, 0.5902799948392307], "y˥˩": [-2.299996002404775, 0.5814522436767432], "y˧˥": [-2.0422859576126373, 0.606484327981546], "y˨˩˦": [-2.254624482193023, 0.5624068138239253], "y˩": [-2.4514219285702934, 0.709385601935554], "z̩": [-3.195526296411515, 0.29048556105623524], "z̩˥": [-2.401914745749134, 0.5740498161966016], "z̩˥˩": [-2.465622293080675, 0.49222007621990754], "z̩˧": [-2.4991084895038314, 0.6063462726674205], "z̩˧˥": [-2.3761833116490836, 0.5859034300843385], "z̩˨˩˦": [-2.4824375237641507, 0.5601644080266962], "z̩˩": [-2.6124471522996395, 0.5982858996975068], "ŋ": [-2.548242839860468, 0.45710037599382536], "ŋ̍": [-4.055864001918101, 0.7768376041069883], "ɕ": [-2.19045792922345, 0.36663538754844577], "ɕʷ": [-2.2014070445099025, 0.3459902865760758], "ə": [-2.5430066303350385, 0.535205438722738], "ə˥": [-2.934460862487925, 0.46605805862082744], "ə˥˩": [-3.538576374990915, 0.6070126836791996], "ə˧": [-2.6435792392987802, 0.5405164150003383], "ə˧˥": [-4.361026941199642, 0.6630132066681234], "ə˨˩˦": [-3.888488042592076, 0.18300384979826886], "ej": [-1.8891859381988543, 0.4467831714679377], "ej˥": [-2.3596419390061127, 0.46752504913129744], "ej˥˩": [-2.370581687384675, 0.5180278459801086], "ej˧˥": [-2.3696759658503037, 0.5511723016976955], "aw˩": [-2.0120182302758542, 0.49272073413111506], "a˥": [-2.47232174622421, 0.5170763265217876], "aj˧": [-4.0558649953288075, 0.7768361992120928], "f": [-2.2837654371954974, 0.4037449368952423], "aj˧˥": [-2.2684013413943576, 0.48283643105451585], "aj˨˩˦": [-2.216015515901684, 0.38792762635774247], "aj˩": [-2.2560624251523747, 0.47575303464167606], "aw˥": [-2.0640693214860653, 0.3538688765452328], "aw˥˩": [-2.1329187754485366, 0.40438591374922955], "aw˧": [-2.384019766002452, 0.3929214041463182], "aw˧˥": [-2.137193288870127, 0.43540172162829827], "ej˨˩˦": [-2.4083046639087855, 0.48355956537529643], "ej˩": [-2.2620101457152098, 0.5845149803544231], "e˥": [-2.6609659799681946, 0.5429393381116399], "e˥˩": [-2.6392855021685677, 0.5136829070822199], "e˧": [-2.6946605488805333, 0.5063090282021141], "e˧˥": [-2.5632419773194988, 0.520645124110837], "e˨˩˦": [-2.7364746874328323, 0.4761052283608704], "e˩": [-2.4921823099047993, 0.49572634044162006], "kʰ": [-2.2226409683980775, 0.4032519817557641], "kʷ": [-2.5737909028274544, 0.45663579158987544], "l": [-2.96978729306177, 0.6993154516594091], "m": [-2.6114668768264035, 0.37635308368829823], "mʲ": [-2.6296761448282866, 0.3488055472715996], "n": [-2.618609878490004, 0.4600220763513909], "a": [-1.8959410967630388, 0.7124343205582678], "aj˥": [-2.211777738690042, 0.4000534691391207], "aj": [-4.605170841639577, 6.664003265340688e-07], "i˧": [-2.5390125561701833, 0.5371806578602595], "m̩˧": [-2.2796449996232058, 0.5332498317936077], "ə˩": [-2.8192253469616033, 0.4940573729826045], "ɥ": [-2.584103403636069, 0.4526318189399375], "ɲ": [-2.630195157167984, 0.40598800133011825], "ɻ": [-2.4636421981968324, 0.4834262095327596], "ʂ": [-2.1998379370310053, 0.39653859897211996], "ʈʂ": [-2.523468055503317, 0.37510446960370447], "ʈʂʰ": [-2.2356068354422107, 0.36337539758925574], "ʎ": [-3.7628179378466013, 0.916301893211793], "ʐ": [-2.4697129866515914, 0.4639092501672924], "ʐ̩": [-3.12050321956227, 0.21430757579554058], "ʐ̩˥": [-2.56105085465946, 0.5357815580745212], "ʐ̩˥˩": [-2.4146679918319007, 0.5780162305231988], "ʐ̩˧": [-3.079964924093529, 0.5301511660378833], "ʐ̩˧˥": [-2.63020222775115, 0.5612381276142274], "ʐ̩˨˩˦": [-2.6249176395105516, 0.546696891305767], "ʐ̩˩": [-2.781815267836966, 0.5113876837688727], "ʔ": [-2.660700980615961, 0.5155557915104646]}}
|
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 sha256:830540952d184bdb56fbc0afd42406765d39519c808a9c584d03ef2cc4d47d12
|
| 3 |
+
size 561319
|
dictionary/mandarin_china_mfa.dict
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
dictionary/mandarin_taiwan_mfa.dict
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
dictionary/rules.yaml
CHANGED
|
@@ -1,244 +1,244 @@
|
|
| 1 |
dialects:
|
| 2 |
china:
|
| 3 |
- following_context: ''
|
| 4 |
-
non_silence_before_correction: 0.
|
| 5 |
preceding_context: ''
|
| 6 |
-
probability: 0.
|
| 7 |
replacement: ''
|
| 8 |
segment: ʔ
|
| 9 |
-
silence_after_probability:
|
| 10 |
-
silence_before_correction:
|
| 11 |
- following_context: ''
|
| 12 |
non_silence_before_correction: 0.09
|
| 13 |
preceding_context: ''
|
| 14 |
probability: 0.05
|
| 15 |
replacement: ''
|
| 16 |
segment: ɻ
|
| 17 |
-
silence_after_probability: 1.
|
| 18 |
-
silence_before_correction: -0.
|
| 19 |
- following_context: ''
|
| 20 |
-
non_silence_before_correction: 0.
|
| 21 |
preceding_context: ''
|
| 22 |
-
probability: 0.
|
| 23 |
replacement: mʲ
|
| 24 |
segment: m j
|
| 25 |
-
silence_after_probability: 0.
|
| 26 |
-
silence_before_correction: -0.
|
| 27 |
- following_context: ''
|
| 28 |
-
non_silence_before_correction: 0.
|
| 29 |
preceding_context: ''
|
| 30 |
-
probability: 0.
|
| 31 |
replacement: ʎ
|
| 32 |
segment: l j
|
| 33 |
-
silence_after_probability:
|
| 34 |
-
silence_before_correction: -0.
|
| 35 |
- following_context: ''
|
| 36 |
-
non_silence_before_correction: 0.
|
| 37 |
preceding_context: ''
|
| 38 |
-
probability: 0.
|
| 39 |
replacement: ɲ
|
| 40 |
segment: n j
|
| 41 |
-
silence_after_probability: 1.
|
| 42 |
silence_before_correction: -0.19
|
| 43 |
- following_context: ''
|
| 44 |
non_silence_before_correction: -0.05
|
| 45 |
preceding_context: ''
|
| 46 |
-
probability: 0.
|
| 47 |
replacement: tʲ
|
| 48 |
segment: tʰ j
|
| 49 |
-
silence_after_probability: 0.
|
| 50 |
-
silence_before_correction: 0.
|
| 51 |
- following_context: ''
|
| 52 |
-
non_silence_before_correction: 0.
|
| 53 |
preceding_context: ''
|
| 54 |
-
probability: 0.
|
| 55 |
replacement: tʲ
|
| 56 |
segment: t j
|
| 57 |
-
silence_after_probability:
|
| 58 |
-
silence_before_correction: -0.
|
| 59 |
- following_context: ''
|
| 60 |
-
non_silence_before_correction:
|
| 61 |
preceding_context: ''
|
| 62 |
probability: 0.06
|
| 63 |
replacement: pʲ
|
| 64 |
segment: pʰ j
|
| 65 |
-
silence_after_probability: 0.
|
| 66 |
-
silence_before_correction: 0.
|
| 67 |
- following_context: ''
|
| 68 |
-
non_silence_before_correction:
|
| 69 |
preceding_context: ''
|
| 70 |
-
probability: 0.
|
| 71 |
replacement: pʲ
|
| 72 |
segment: p j
|
| 73 |
-
silence_after_probability: 1.
|
| 74 |
-
silence_before_correction: -0.
|
| 75 |
- following_context: ''
|
| 76 |
-
non_silence_before_correction: 0.
|
| 77 |
preceding_context: ''
|
| 78 |
-
probability: 0.
|
| 79 |
replacement: pʷ
|
| 80 |
segment: pʰ w
|
| 81 |
-
silence_after_probability:
|
| 82 |
-
silence_before_correction: -0.
|
| 83 |
- following_context: ''
|
| 84 |
-
non_silence_before_correction:
|
| 85 |
preceding_context: ''
|
| 86 |
probability: 0.03
|
| 87 |
replacement: pʷ
|
| 88 |
segment: p w
|
| 89 |
-
silence_after_probability: 2.
|
| 90 |
-
silence_before_correction: -0.
|
| 91 |
- following_context: ''
|
| 92 |
-
non_silence_before_correction:
|
| 93 |
preceding_context: ''
|
| 94 |
-
probability: 0.
|
| 95 |
replacement: tʷ
|
| 96 |
segment: tʰ w
|
| 97 |
-
silence_after_probability: 0.
|
| 98 |
-
silence_before_correction: 0.
|
| 99 |
- following_context: ''
|
| 100 |
-
non_silence_before_correction: -0.
|
| 101 |
preceding_context: ''
|
| 102 |
-
probability: 0.
|
| 103 |
replacement: tʷ
|
| 104 |
segment: t w
|
| 105 |
-
silence_after_probability:
|
| 106 |
-
silence_before_correction: 0.
|
| 107 |
- following_context: ''
|
| 108 |
-
non_silence_before_correction: 0.
|
| 109 |
preceding_context: ''
|
| 110 |
probability: 0.01
|
| 111 |
replacement: kʷ
|
| 112 |
segment: kʰ w
|
| 113 |
silence_after_probability: 1.92
|
| 114 |
-
silence_before_correction: -0.
|
| 115 |
- following_context: ''
|
| 116 |
-
non_silence_before_correction: 0.
|
| 117 |
preceding_context: ''
|
| 118 |
probability: 0.01
|
| 119 |
replacement: kʷ
|
| 120 |
segment: k w
|
| 121 |
-
silence_after_probability:
|
| 122 |
-
silence_before_correction: -0.
|
| 123 |
taiwan:
|
| 124 |
- following_context: ''
|
| 125 |
-
non_silence_before_correction: 0.
|
| 126 |
preceding_context: ''
|
| 127 |
probability: 0.04
|
| 128 |
replacement: ''
|
| 129 |
segment: ʔ
|
| 130 |
-
silence_after_probability: 1.
|
| 131 |
-
silence_before_correction: -0.
|
| 132 |
- following_context: ''
|
| 133 |
-
non_silence_before_correction: 0.
|
| 134 |
preceding_context: ''
|
| 135 |
probability: 0.02
|
| 136 |
replacement: ''
|
| 137 |
segment: ɻ
|
| 138 |
-
silence_after_probability: 0.
|
| 139 |
-
silence_before_correction: 0.
|
| 140 |
- following_context: ''
|
| 141 |
-
non_silence_before_correction: -0.
|
| 142 |
preceding_context: ''
|
| 143 |
probability: 0.01
|
| 144 |
replacement: mʲ
|
| 145 |
segment: m j
|
| 146 |
-
silence_after_probability: 0.
|
| 147 |
-
silence_before_correction: 0.
|
| 148 |
- following_context: ''
|
| 149 |
-
non_silence_before_correction:
|
| 150 |
preceding_context: ''
|
| 151 |
-
probability: 0.
|
| 152 |
replacement: ʎ
|
| 153 |
segment: l j
|
| 154 |
-
silence_after_probability: 3.
|
| 155 |
-
silence_before_correction: -0.
|
| 156 |
- following_context: ''
|
| 157 |
-
non_silence_before_correction: 0.
|
| 158 |
preceding_context: ''
|
| 159 |
probability: 0.01
|
| 160 |
replacement: ɲ
|
| 161 |
segment: n j
|
| 162 |
-
silence_after_probability:
|
| 163 |
-
silence_before_correction: -0.
|
| 164 |
- following_context: ''
|
| 165 |
-
non_silence_before_correction: -0.
|
| 166 |
preceding_context: ''
|
| 167 |
-
probability: 0.
|
| 168 |
replacement: tʲ
|
| 169 |
segment: tʰ j
|
| 170 |
-
silence_after_probability: 0.
|
| 171 |
-
silence_before_correction: 0.
|
| 172 |
- following_context: ''
|
| 173 |
-
non_silence_before_correction: 0.
|
| 174 |
preceding_context: ''
|
| 175 |
probability: 0.01
|
| 176 |
replacement: tʲ
|
| 177 |
segment: t j
|
| 178 |
-
silence_after_probability:
|
| 179 |
-
silence_before_correction: -0.
|
| 180 |
- following_context: ''
|
| 181 |
-
non_silence_before_correction: 0.
|
| 182 |
preceding_context: ''
|
| 183 |
probability: 0.02
|
| 184 |
replacement: pʲ
|
| 185 |
segment: pʰ j
|
| 186 |
-
silence_after_probability: 0.
|
| 187 |
-
silence_before_correction:
|
| 188 |
- following_context: ''
|
| 189 |
-
non_silence_before_correction: -0.
|
| 190 |
preceding_context: ''
|
| 191 |
probability: 0.01
|
| 192 |
replacement: pʲ
|
| 193 |
segment: p j
|
| 194 |
-
silence_after_probability:
|
| 195 |
-
silence_before_correction: 0.
|
| 196 |
- following_context: ''
|
| 197 |
-
non_silence_before_correction: 0.
|
| 198 |
preceding_context: ''
|
| 199 |
probability: 0.01
|
| 200 |
replacement: pʷ
|
| 201 |
segment: pʰ w
|
| 202 |
-
silence_after_probability:
|
| 203 |
-
silence_before_correction: -0.
|
| 204 |
- following_context: ''
|
| 205 |
-
non_silence_before_correction: 0.
|
| 206 |
preceding_context: ''
|
| 207 |
probability: 0.01
|
| 208 |
replacement: pʷ
|
| 209 |
segment: p w
|
| 210 |
-
silence_after_probability: 3.
|
| 211 |
-
silence_before_correction: -0.
|
| 212 |
- following_context: ''
|
| 213 |
non_silence_before_correction: -0.01
|
| 214 |
preceding_context: ''
|
| 215 |
-
probability: 0.
|
| 216 |
replacement: tʷ
|
| 217 |
segment: tʰ w
|
| 218 |
-
silence_after_probability: 1.
|
| 219 |
-
silence_before_correction: -0.
|
| 220 |
- following_context: ''
|
| 221 |
-
non_silence_before_correction:
|
| 222 |
preceding_context: ''
|
| 223 |
probability: 0.01
|
| 224 |
replacement: tʷ
|
| 225 |
segment: t w
|
| 226 |
-
silence_after_probability: 2.
|
| 227 |
-
silence_before_correction: -0.
|
| 228 |
- following_context: ''
|
| 229 |
-
non_silence_before_correction: -0.
|
| 230 |
preceding_context: ''
|
| 231 |
probability: 0.01
|
| 232 |
replacement: kʷ
|
| 233 |
segment: kʰ w
|
| 234 |
-
silence_after_probability: 1.
|
| 235 |
-
silence_before_correction: 0.
|
| 236 |
- following_context: ''
|
| 237 |
-
non_silence_before_correction: -0.
|
| 238 |
preceding_context: ''
|
| 239 |
probability: 0.01
|
| 240 |
replacement: kʷ
|
| 241 |
segment: k w
|
| 242 |
-
silence_after_probability: 2.
|
| 243 |
-
silence_before_correction: -0.
|
| 244 |
rules: []
|
|
|
|
| 1 |
dialects:
|
| 2 |
china:
|
| 3 |
- following_context: ''
|
| 4 |
+
non_silence_before_correction: 0.05
|
| 5 |
preceding_context: ''
|
| 6 |
+
probability: 0.3
|
| 7 |
replacement: ''
|
| 8 |
segment: ʔ
|
| 9 |
+
silence_after_probability: 1.0
|
| 10 |
+
silence_before_correction: 0.01
|
| 11 |
- following_context: ''
|
| 12 |
non_silence_before_correction: 0.09
|
| 13 |
preceding_context: ''
|
| 14 |
probability: 0.05
|
| 15 |
replacement: ''
|
| 16 |
segment: ɻ
|
| 17 |
+
silence_after_probability: 1.67
|
| 18 |
+
silence_before_correction: -0.12
|
| 19 |
- following_context: ''
|
| 20 |
+
non_silence_before_correction: 0.01
|
| 21 |
preceding_context: ''
|
| 22 |
+
probability: 0.06
|
| 23 |
replacement: mʲ
|
| 24 |
segment: m j
|
| 25 |
+
silence_after_probability: 0.5
|
| 26 |
+
silence_before_correction: -0.1
|
| 27 |
- following_context: ''
|
| 28 |
+
non_silence_before_correction: 0.02
|
| 29 |
preceding_context: ''
|
| 30 |
+
probability: 0.04
|
| 31 |
replacement: ʎ
|
| 32 |
segment: l j
|
| 33 |
+
silence_after_probability: 2.22
|
| 34 |
+
silence_before_correction: -0.12
|
| 35 |
- following_context: ''
|
| 36 |
+
non_silence_before_correction: 0.03
|
| 37 |
preceding_context: ''
|
| 38 |
+
probability: 0.09
|
| 39 |
replacement: ɲ
|
| 40 |
segment: n j
|
| 41 |
+
silence_after_probability: 1.42
|
| 42 |
silence_before_correction: -0.19
|
| 43 |
- following_context: ''
|
| 44 |
non_silence_before_correction: -0.05
|
| 45 |
preceding_context: ''
|
| 46 |
+
probability: 0.14
|
| 47 |
replacement: tʲ
|
| 48 |
segment: tʰ j
|
| 49 |
+
silence_after_probability: 0.21
|
| 50 |
+
silence_before_correction: 0.09
|
| 51 |
- following_context: ''
|
| 52 |
+
non_silence_before_correction: 0.01
|
| 53 |
preceding_context: ''
|
| 54 |
+
probability: 0.04
|
| 55 |
replacement: tʲ
|
| 56 |
segment: t j
|
| 57 |
+
silence_after_probability: 1.52
|
| 58 |
+
silence_before_correction: -0.1
|
| 59 |
- following_context: ''
|
| 60 |
+
non_silence_before_correction: 0.01
|
| 61 |
preceding_context: ''
|
| 62 |
probability: 0.06
|
| 63 |
replacement: pʲ
|
| 64 |
segment: pʰ j
|
| 65 |
+
silence_after_probability: 0.56
|
| 66 |
+
silence_before_correction: -0.08
|
| 67 |
- following_context: ''
|
| 68 |
+
non_silence_before_correction: 0.01
|
| 69 |
preceding_context: ''
|
| 70 |
+
probability: 0.01
|
| 71 |
replacement: pʲ
|
| 72 |
segment: p j
|
| 73 |
+
silence_after_probability: 1.41
|
| 74 |
+
silence_before_correction: -0.09
|
| 75 |
- following_context: ''
|
| 76 |
+
non_silence_before_correction: -0.02
|
| 77 |
preceding_context: ''
|
| 78 |
+
probability: 0.02
|
| 79 |
replacement: pʷ
|
| 80 |
segment: pʰ w
|
| 81 |
+
silence_after_probability: 0.91
|
| 82 |
+
silence_before_correction: -0.08
|
| 83 |
- following_context: ''
|
| 84 |
+
non_silence_before_correction: 0.07
|
| 85 |
preceding_context: ''
|
| 86 |
probability: 0.03
|
| 87 |
replacement: pʷ
|
| 88 |
segment: p w
|
| 89 |
+
silence_after_probability: 2.62
|
| 90 |
+
silence_before_correction: -0.21
|
| 91 |
- following_context: ''
|
| 92 |
+
non_silence_before_correction: 0.07
|
| 93 |
preceding_context: ''
|
| 94 |
+
probability: 0.15
|
| 95 |
replacement: tʷ
|
| 96 |
segment: tʰ w
|
| 97 |
+
silence_after_probability: 0.87
|
| 98 |
+
silence_before_correction: -0.2
|
| 99 |
- following_context: ''
|
| 100 |
+
non_silence_before_correction: -0.01
|
| 101 |
preceding_context: ''
|
| 102 |
+
probability: 0.05
|
| 103 |
replacement: tʷ
|
| 104 |
segment: t w
|
| 105 |
+
silence_after_probability: 0.79
|
| 106 |
+
silence_before_correction: 0.04
|
| 107 |
- following_context: ''
|
| 108 |
+
non_silence_before_correction: 0.0
|
| 109 |
preceding_context: ''
|
| 110 |
probability: 0.01
|
| 111 |
replacement: kʷ
|
| 112 |
segment: kʰ w
|
| 113 |
silence_after_probability: 1.92
|
| 114 |
+
silence_before_correction: -0.08
|
| 115 |
- following_context: ''
|
| 116 |
+
non_silence_before_correction: 0.03
|
| 117 |
preceding_context: ''
|
| 118 |
probability: 0.01
|
| 119 |
replacement: kʷ
|
| 120 |
segment: k w
|
| 121 |
+
silence_after_probability: 2.72
|
| 122 |
+
silence_before_correction: -0.17
|
| 123 |
taiwan:
|
| 124 |
- following_context: ''
|
| 125 |
+
non_silence_before_correction: 0.07
|
| 126 |
preceding_context: ''
|
| 127 |
probability: 0.04
|
| 128 |
replacement: ''
|
| 129 |
segment: ʔ
|
| 130 |
+
silence_after_probability: 1.62
|
| 131 |
+
silence_before_correction: -0.17
|
| 132 |
- following_context: ''
|
| 133 |
+
non_silence_before_correction: 0.07
|
| 134 |
preceding_context: ''
|
| 135 |
probability: 0.02
|
| 136 |
replacement: ''
|
| 137 |
segment: ɻ
|
| 138 |
+
silence_after_probability: 0.58
|
| 139 |
+
silence_before_correction: -0.09
|
| 140 |
- following_context: ''
|
| 141 |
+
non_silence_before_correction: -0.03
|
| 142 |
preceding_context: ''
|
| 143 |
probability: 0.01
|
| 144 |
replacement: mʲ
|
| 145 |
segment: m j
|
| 146 |
+
silence_after_probability: 0.5
|
| 147 |
+
silence_before_correction: 0.05
|
| 148 |
- following_context: ''
|
| 149 |
+
non_silence_before_correction: 0.01
|
| 150 |
preceding_context: ''
|
| 151 |
+
probability: 0.02
|
| 152 |
replacement: ʎ
|
| 153 |
segment: l j
|
| 154 |
+
silence_after_probability: 3.56
|
| 155 |
+
silence_before_correction: -0.09
|
| 156 |
- following_context: ''
|
| 157 |
+
non_silence_before_correction: 0.04
|
| 158 |
preceding_context: ''
|
| 159 |
probability: 0.01
|
| 160 |
replacement: ɲ
|
| 161 |
segment: n j
|
| 162 |
+
silence_after_probability: 1.26
|
| 163 |
+
silence_before_correction: -0.18
|
| 164 |
- following_context: ''
|
| 165 |
+
non_silence_before_correction: -0.02
|
| 166 |
preceding_context: ''
|
| 167 |
+
probability: 0.03
|
| 168 |
replacement: tʲ
|
| 169 |
segment: tʰ j
|
| 170 |
+
silence_after_probability: 0.53
|
| 171 |
+
silence_before_correction: 0.09
|
| 172 |
- following_context: ''
|
| 173 |
+
non_silence_before_correction: 0.01
|
| 174 |
preceding_context: ''
|
| 175 |
probability: 0.01
|
| 176 |
replacement: tʲ
|
| 177 |
segment: t j
|
| 178 |
+
silence_after_probability: 1.68
|
| 179 |
+
silence_before_correction: -0.1
|
| 180 |
- following_context: ''
|
| 181 |
+
non_silence_before_correction: -0.02
|
| 182 |
preceding_context: ''
|
| 183 |
probability: 0.02
|
| 184 |
replacement: pʲ
|
| 185 |
segment: pʰ j
|
| 186 |
+
silence_after_probability: 0.5
|
| 187 |
+
silence_before_correction: 0.03
|
| 188 |
- following_context: ''
|
| 189 |
+
non_silence_before_correction: -0.02
|
| 190 |
preceding_context: ''
|
| 191 |
probability: 0.01
|
| 192 |
replacement: pʲ
|
| 193 |
segment: p j
|
| 194 |
+
silence_after_probability: 1.31
|
| 195 |
+
silence_before_correction: -0.01
|
| 196 |
- following_context: ''
|
| 197 |
+
non_silence_before_correction: 0.11
|
| 198 |
preceding_context: ''
|
| 199 |
probability: 0.01
|
| 200 |
replacement: pʷ
|
| 201 |
segment: pʰ w
|
| 202 |
+
silence_after_probability: 2.27
|
| 203 |
+
silence_before_correction: -0.3
|
| 204 |
- following_context: ''
|
| 205 |
+
non_silence_before_correction: 0.12
|
| 206 |
preceding_context: ''
|
| 207 |
probability: 0.01
|
| 208 |
replacement: pʷ
|
| 209 |
segment: p w
|
| 210 |
+
silence_after_probability: 3.95
|
| 211 |
+
silence_before_correction: -0.32
|
| 212 |
- following_context: ''
|
| 213 |
non_silence_before_correction: -0.01
|
| 214 |
preceding_context: ''
|
| 215 |
+
probability: 0.02
|
| 216 |
replacement: tʷ
|
| 217 |
segment: tʰ w
|
| 218 |
+
silence_after_probability: 1.22
|
| 219 |
+
silence_before_correction: -0.08
|
| 220 |
- following_context: ''
|
| 221 |
+
non_silence_before_correction: 0.01
|
| 222 |
preceding_context: ''
|
| 223 |
probability: 0.01
|
| 224 |
replacement: tʷ
|
| 225 |
segment: t w
|
| 226 |
+
silence_after_probability: 2.26
|
| 227 |
+
silence_before_correction: -0.05
|
| 228 |
- following_context: ''
|
| 229 |
+
non_silence_before_correction: -0.06
|
| 230 |
preceding_context: ''
|
| 231 |
probability: 0.01
|
| 232 |
replacement: kʷ
|
| 233 |
segment: kʰ w
|
| 234 |
+
silence_after_probability: 1.35
|
| 235 |
+
silence_before_correction: 0.01
|
| 236 |
- following_context: ''
|
| 237 |
+
non_silence_before_correction: -0.02
|
| 238 |
preceding_context: ''
|
| 239 |
probability: 0.01
|
| 240 |
replacement: kʷ
|
| 241 |
segment: k w
|
| 242 |
+
silence_after_probability: 2.44
|
| 243 |
+
silence_before_correction: -0.1
|
| 244 |
rules: []
|
g2p/mandarin_china_mfa/meta.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"version": "3.0.0", "architecture": "phonetisaurus", "train_date": "2024-02-23 16:58:56.188869", "phones": ["a\u02e9", "
|
|
|
|
| 1 |
+
{"version": "3.0.0", "architecture": "phonetisaurus", "train_date": "2024-02-23 16:58:56.188869", "phones": ["a\u02e5\u02e9", "\u0259\u02e8\u02e9\u02e6", "z\u0329\u02e9", "m\u0329", "k\u02b0", "e\u02e7", "\u0290\u0329\u02e8\u02e9\u02e6", "aj\u02e5\u02e9", "ej\u02e7", "k", "y\u02e5\u02e9", "e", "u\u02e5\u02e9", "w", "aw\u02e7", "ej\u02e9", "\u028e", "\u0288\u0282\u02b0", "n\u0329\u02e7\u02e5", "\u0290\u0329\u02e5", "e\u02e8\u02e9\u02e6", "s", "p\u02b0", "\u0288\u0282", "u", "o", "e\u02e5", "ej", "ej\u02e7\u02e5", "i\u02e5\u02e9", "ow\u02e7\u02e5", "u\u02e7", "ow\u02e5\u02e9", "\u0259\u02e5\u02e9", "t\u0255\u02b0", "y\u02e8\u02e9\u02e6", "z\u0329\u02e8\u02e9\u02e6", "ej\u02e5\u02e9", "aw", "a\u02e7", "\u0290", "ts\u02b0", "o\u02e7", "e\u02e5\u02e9", "j", "ts", "\u014b\u030d\u02e7\u02e5", "y", "p\u02b7", "\u0290\u0329", "\u0259\u02e7", "aw\u02e7\u02e5", "\u0259", "\u0272", "u\u02e5", "\u0294", "z\u0329\u02e7", "\u027b", "\u0259\u02e7\u02e5", "m", "\u0282", "\u0290\u0329\u02e5\u02e9", "t", "ow", "aw\u02e8\u02e9\u02e6", "p", "i\u02e5", "t\u0255\u02b7", "t\u02b2", "aj\u02e8\u02e9\u02e6", "\u014b\u030d", "e\u02e9", "f", "z\u0329", "a", "aj\u02e7\u02e5", "m\u02b2", "\u0255", "\u0290\u0329\u02e7", "u\u02e9", "o\u02e7\u02e5", "z\u0329\u02e5", "m\u0329\u02e5\u02e9", "i\u02e8\u02e9\u02e6", "p\u02b2", "x", "aw\u02e5\u02e9", "a\u02e7\u02e5", "ow\u02e7", "\u0265", "a\u02e5", "y\u02e7\u02e5", "i\u02e9", "\u0290\u0329\u02e9", "m\u0329\u02e8\u02e9\u02e6", "e\u02e7\u02e5", "k\u02b7", "o\u02e8\u02e9\u02e6", "z\u0329\u02e5\u02e9", "t\u02b0", "y\u02e7", "\u0259\u02e5", "o\u02e9", "o\u02e5", "i\u02e7\u02e5", "aj\u02e7", "x\u02b7", "i", "ej\u02e8\u02e9\u02e6", "t\u02b7", "t\u0255", "i\u02e7", "\u0290\u0329\u02e7\u02e5", "a\u02e9", "aw\u02e9", "o\u02e5\u02e9", "m\u0329\u02e5", "a\u02e8\u02e9\u02e6", "u\u02e8\u02e9\u02e6", "ej\u02e5", "ow\u02e9", "aj", "aj\u02e9", "\u0255\u02b7", "z\u0329\u02e7\u02e5", "ow\u02e5", "ow\u02e8\u02e9\u02e6", "\u014b", "m\u0329\u02e7\u02e5", "\u0259\u02e9", "n", "aj\u02e5", "l", "y\u02e9", "aw\u02e5", "y\u02e5", "u\u02e7\u02e5"], "graphemes": ["\u0113", "\u01d4", "i", "\u00e8", "\u00f2", "f", "j", "\u01ce", "y", "a", "\u0101", "\u00e1", "c", "k", "e", "b", "z", "w", "\u01d2", "\u01d0", "\u012b", "\u01dc", "\u014d", "s", "q", "x", "\u00e0", "m", "u", "o", "d", "\u01d8", "\u00f9", "\u01da", "'", "t", "\u011b", "\u016b", "\u00e9", "p", "\u00fc", "n", "\u00fa", "\u00ec", "r", "l", "g", "\u00f3", "h", "\u00ed"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "evaluation": {"num_words": 10700, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 96301, "num_graphemes": 50, "num_phones": 137}, "unicode_decomposition": false}
|
g2p/mandarin_taiwan_mfa/meta.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"version": "3.0.0", "architecture": "phonetisaurus", "train_date": "2024-02-23 17:30:47.846351", "phones": ["a\u02e9", "
|
|
|
|
| 1 |
+
{"version": "3.0.0", "architecture": "phonetisaurus", "train_date": "2024-02-23 17:30:47.846351", "phones": ["a\u02e5\u02e9", "\u0259\u02e8\u02e9\u02e6", "z\u0329\u02e9", "m\u0329", "k\u02b0", "e\u02e7", "\u0290\u0329\u02e8\u02e9\u02e6", "aj\u02e5\u02e9", "ej\u02e7", "k", "y\u02e5\u02e9", "e", "u\u02e5\u02e9", "w", "aw\u02e7", "ej\u02e9", "\u028e", "\u0288\u0282\u02b0", "n\u0329\u02e7\u02e5", "\u0290\u0329\u02e5", "e\u02e8\u02e9\u02e6", "s", "p\u02b0", "\u0288\u0282", "u", "o", "e\u02e5", "ej", "ej\u02e7\u02e5", "i\u02e5\u02e9", "ow\u02e7\u02e5", "u\u02e7", "ow\u02e5\u02e9", "\u0259\u02e5\u02e9", "t\u0255\u02b0", "y\u02e8\u02e9\u02e6", "z\u0329\u02e8\u02e9\u02e6", "ej\u02e5\u02e9", "aw", "a\u02e7", "\u0290", "ts\u02b0", "o\u02e7", "e\u02e5\u02e9", "j", "ts", "\u014b\u030d\u02e7\u02e5", "y", "p\u02b7", "\u0290\u0329", "\u0259\u02e7", "aw\u02e7\u02e5", "\u0259", "\u0272", "u\u02e5", "\u0294", "z\u0329\u02e7", "\u027b", "\u0259\u02e7\u02e5", "m", "\u0282", "\u0290\u0329\u02e5\u02e9", "t", "ow", "aw\u02e8\u02e9\u02e6", "p", "i\u02e5", "t\u0255\u02b7", "t\u02b2", "aj\u02e8\u02e9\u02e6", "\u014b\u030d", "e\u02e9", "f", "z\u0329", "a", "aj\u02e7\u02e5", "m\u02b2", "\u0255", "\u0290\u0329\u02e7", "u\u02e9", "o\u02e7\u02e5", "z\u0329\u02e5", "m\u0329\u02e5\u02e9", "i\u02e8\u02e9\u02e6", "p\u02b2", "x", "aw\u02e5\u02e9", "a\u02e7\u02e5", "ow\u02e7", "\u0265", "a\u02e5", "y\u02e7\u02e5", "i\u02e9", "\u0290\u0329\u02e9", "m\u0329\u02e8\u02e9\u02e6", "e\u02e7\u02e5", "k\u02b7", "o\u02e8\u02e9\u02e6", "z\u0329\u02e5\u02e9", "t\u02b0", "y\u02e7", "\u0259\u02e5", "o\u02e9", "o\u02e5", "i\u02e7\u02e5", "aj\u02e7", "x\u02b7", "i", "ej\u02e8\u02e9\u02e6", "t\u02b7", "t\u0255", "i\u02e7", "\u0290\u0329\u02e7\u02e5", "a\u02e9", "aw\u02e9", "o\u02e5\u02e9", "m\u0329\u02e5", "a\u02e8\u02e9\u02e6", "u\u02e8\u02e9\u02e6", "ej\u02e5", "ow\u02e9", "aj", "aj\u02e9", "\u0255\u02b7", "z\u0329\u02e7\u02e5", "ow\u02e5", "ow\u02e8\u02e9\u02e6", "\u014b", "m\u0329\u02e7\u02e5", "\u0259\u02e9", "n", "aj\u02e5", "l", "y\u02e9", "aw\u02e5", "y\u02e5", "u\u02e7\u02e5"], "graphemes": ["\u0113", "\u01d4", "i", "\u00e8", "\u00f2", "f", "j", "\u01ce", "y", "a", "\u0101", "\u00e1", "c", "k", "e", "b", "z", "w", "\u01d2", "\u01d0", "\u012b", "\u01dc", "\u014d", "s", "q", "x", "\u00e0", "m", "u", "o", "d", "\u01d8", "\u00f9", "\u01da", "'", "t", "\u011b", "\u016b", "\u00e9", "p", "\u00fc", "n", "\u00fa", "\u00ec", "r", "l", "g", "\u00f3", "h", "\u00ed"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "evaluation": {"num_words": 10379, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 93422, "num_graphemes": 50, "num_phones": 137}, "unicode_decomposition": false}
|