mmcauliffe commited on
Commit
fdc6edc
·
verified ·
1 Parent(s): 5e04933

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -77,7 +77,7 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
77
  - **Source:** wikipron
78
  - **Orthography:** Latin
79
  - **Phone set:** MFA
80
- - **Words:** 147,701
81
  * **Phones:** 44
82
  * **Graphemes:** 47
83
 
@@ -124,13 +124,12 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
124
  - **Source:** https://voice.mozilla.org/en/datasets
125
  - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
126
  - **Dialects:** N/A
127
- - **Number of hours:** 39.97
128
- - **Number of utterances:** 37,302
129
- - **Number of speakers:** 674
130
- - **Female speakers:** 19
131
- - **Male speakers:** 128
132
- - **Unknown speakers:** 527
133
-
134
 
135
  #### GlobalPhone Swedish
136
 
@@ -138,27 +137,24 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
138
  - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
139
  - **Dialects:** N/A
140
  - **Number of hours:** 21.69
141
- - **Number of utterances:** 11,816
142
  - **Number of speakers:** 98
143
  - **Female speakers:** 48
144
  - **Male speakers:** 50
145
  - **Unknown speakers:** 0
146
 
147
-
148
  #### NST Swedish
149
 
150
  - **Source:** https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-56/
151
  - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
152
  - **Dialects:** N/A
153
- - **Number of hours:** 378.33
154
- - **Number of utterances:** 276,372
155
- - **Number of speakers:** 895
156
  - **Female speakers:** 482
157
  - **Male speakers:** 407
158
  - **Unknown speakers:** 6
159
 
160
-
161
-
162
  ### Training Procedure
163
 
164
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
77
  - **Source:** wikipron
78
  - **Orthography:** Latin
79
  - **Phone set:** MFA
80
+ - **Words:** 147,702
81
  * **Phones:** 44
82
  * **Graphemes:** 47
83
 
 
124
  - **Source:** https://voice.mozilla.org/en/datasets
125
  - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
126
  - **Dialects:** N/A
127
+ - **Number of hours:** 40.07
128
+ - **Number of utterances:** 37,312
129
+ - **Number of speakers:** 677
130
+ - **Female speakers:** 0
131
+ - **Male speakers:** 3
132
+ - **Unknown speakers:** 1
 
133
 
134
  #### GlobalPhone Swedish
135
 
 
137
  - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
138
  - **Dialects:** N/A
139
  - **Number of hours:** 21.69
140
+ - **Number of utterances:** 11,814
141
  - **Number of speakers:** 98
142
  - **Female speakers:** 48
143
  - **Male speakers:** 50
144
  - **Unknown speakers:** 0
145
 
 
146
  #### NST Swedish
147
 
148
  - **Source:** https://www.nb.no/sprakbanken/en/resource-catalogue/oai-nb-no-sbr-56/
149
  - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
150
  - **Dialects:** N/A
151
+ - **Number of hours:** 377.27
152
+ - **Number of utterances:** 275,277
153
+ - **Number of speakers:** 891
154
  - **Female speakers:** 482
155
  - **Male speakers:** 407
156
  - **Unknown speakers:** 6
157
 
 
 
158
  ### Training Procedure
159
 
160
  <!-- 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 sha256:000df0ad2889bfa4fbba16ac5541b44294dd9c02de593d6557029c3892b83263
3
- size 50256244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9d9c4db002c211529d5a29efeac761ee8ce8ed527d117ac59f419242273291
3
+ size 50279565
acoustic/final.mdl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaf9ec0842710a4a7d64eaaac4e83cf8b7821a6006ac7a47cd479f26d4ed130d
3
- size 50256244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0c3a8cf2e737e130c2dec140ced46943f0e49f29a11e15137c7400989cd84b
3
+ size 50279565
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", "a˥˧", "a˥˩", "a˧˩", "a˩", "b", "d̪", "eː", "eː˥˧", "eː˥˩", "eː˧˩", "eː˩", "f", "h", "iː", "iː˥˧", "iː˥˩", "iː˧˩", "j", "k", "kʰ", "l̪", "m", "n̪", "oː", "oː˥˧", "oː˥˩", "oː˧˩", "oː˩", "p", "pʰ", "r", "s̪", "t̪", "t̪ʰ", "uː", "uː˥˧", "uː˥˩", "uː˧˩", "yː", "yː˥˧", "yː˥˩", "yː˧˩", "yː˩", "øː", "øː˥˧", "øː˥˩", "øː˧˩", "øː˩", "ŋ", "œ", "œ˥˩", "œ˧˩", "ɑː", "ɑː˥˧", "ɑː˥˩", "ɑː˧˩", "ɑː˩", "ɔ", "ɔ˥˧", "ɔ˥˩", "ɔ˧˩", "ɔ˩", "ɕ", "ɖ", "ɛ", "ɛː", "ɛː˥˧", "ɛː˥˩", "ɛː˧˩", "ɛ˥˧", "ɛ˥˩", "ɛ˧˩", "ɛ˩", "ɡ", "ɧ", "ɪ", "ɪ˥˧", "ɪ˥˩", "ɪ˧˩", "ɪ˩", "ɭ", "ɳ", "ɵ", "ɵ˥˧", "ɵ˥˩", "ɵ˧˩", "ɵ˩", "ʂ", "ʈ", "ʈʰ", "ʉː", "ʉː˥˧", "ʉː˥˩", "ʉː˧˩", "ʊ", "ʊ˥˩", "ʊ˧˩", "ʊ˩", "ʋ", "ʏ", "ʏ˥˧", "ʏ˥˩", "ʏ˧˩", "ʏ˩"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "a˥˧": 4, "a˥˩": 5, "a˧˩": 6, "a˩": 7, "b": 8, "d̪": 9, "eː": 10, "eː˥˧": 11, "eː˥˩": 12, "eː˧˩": 13, "eː˩": 14, "f": 15, "h": 16, "iː": 17, "iː˥˧": 18, "iː˥˩": 19, "iː˧˩": 20, "j": 21, "k": 22, "kʰ": 23, "l̪": 24, "m": 25, "n̪": 26, "oː": 27, "oː˥˧": 28, "oː˥˩": 29, "oː˧˩": 30, "oː˩": 31, "p": 32, "pʰ": 33, "r": 34, "s̪": 35, "t̪": 36, "t̪ʰ": 37, "uː": 38, "uː˥˧": 39, "uː˥˩": 40, "uː˧˩": 41, "yː": 42, "yː˥˧": 43, "yː˥˩": 44, "yː˧˩": 45, "yː˩": 46, "øː": 47, "øː˥˧": 48, "øː˥˩": 49, "øː˧˩": 50, "øː˩": 51, "ŋ": 52, "œ": 53, "œ˥˩": 54, "œ˧˩": 55, "ɑː": 56, "ɑː˥˧": 57, "ɑː˥˩": 58, "ɑː˧˩": 59, "ɑː˩": 60, "ɔ": 61, "ɔ˥˧": 62, "ɔ˥˩": 63, "ɔ˧˩": 64, "ɔ˩": 65, "ɕ": 66, "ɖ": 67, "ɛ": 68, "ɛː": 69, "ɛː˥˧": 70, "ɛː˥˩": 71, "ɛː˧˩": 72, "ɛ˥˧": 73, "ɛ˥˩": 74, "ɛ˧˩": 75, "ɛ˩": 76, "ɡ": 77, "ɧ": 78, "ɪ": 79, "ɪ˥˧": 80, "ɪ˥˩": 81, "ɪ˧˩": 82, "ɪ˩": 83, "ɭ": 84, "ɳ": 85, "ɵ": 86, "ɵ˥˧": 87, "ɵ˥˩": 88, "ɵ˧˩": 89, "ɵ˩": 90, "ʂ": 91, "ʈ": 92, "ʈʰ": 93, "ʉː": 94, "ʉː˥˧": 95, "ʉː˥˩": 96, "ʉː˧˩": 97, "ʊ": 98, "ʊ˥˩": 99, "ʊ˧˩": 100, "ʊ˩": 101, "ʋ": 102, "ʏ": 103, "ʏ˥˧": 104, "ʏ˥˩": 105, "ʏ˧˩": 106, "ʏ˩": 107}, "phone_groups": {"0": ["b"], "1": ["d̪"], "2": ["f"], "3": ["h"], "4": ["j"], "5": ["k", "kʰ"], "6": ["l̪"], "7": ["m"], "8": ["n̪"], "9": ["p", "pʰ"], "10": ["r"], "11": ["s̪"], "12": ["t̪", "t̪ʰ"], "13": ["ŋ"], "14": ["ɕ"], "15": ["ɖ"], "16": ["ɡ"], "17": ["ɧ"], "18": ["ɭ"], "19": ["ɳ"], "20": ["ʂ"], "21": ["ʈ", "ʈʰ"], "22": ["ʋ"], "23": ["a", "a˥˧", "a˥˩", "a˧˩", "a˩"], "24": ["eː", "eː˥˧", "eː˥˩", "eː˧˩", "eː˩"], "25": ["iː", "iː˥˧", "iː˥˩", "iː˧˩"], "26": ["oː", "oː˥˧", "oː˥˩", "oː˧˩", "oː˩"], "27": ["uː", "uː˥˧", "uː˥˩", "uː˧˩"], "28": ["yː", "yː˥˧", "yː˥˩", "yː˧˩", "yː˩"], "29": ["øː", "øː˥˧", "øː˥˩", "øː˧˩", "øː˩"], "30": ["œ", "œ˥˩", "œ˧˩"], "31": ["ɑː", "ɑː˥˧", "ɑː˥˩", "ɑː˧˩", "ɑː˩"], "32": ["ɔ", "ɔ˥˧", "ɔ˥˩", "ɔ˧˩", "ɔ˩"], "33": ["ɛ", "ɛː", "ɛː˥˧", "ɛː˥˩", "ɛː˧˩", "ɛ˥˧", "ɛ˥˩", "ɛ˧˩", "ɛ˩"], "34": ["ɪ", "ɪ˥˧", "ɪ˥˩", "ɪ˧˩", "ɪ˩"], "35": ["ɵ", "ɵ˥˧", "ɵ˥˩", "ɵ˧˩", "ɵ˩"], "36": ["ʉː", "ʉː˥˧", "ʉː˥˩", "ʉː˧˩"], "37": ["ʊ", "ʊ˥˩", "ʊ˧˩", "ʊ˩"], "38": ["ʏ", "ʏ˥˧", "ʏ˥˩", "ʏ˧˩", "ʏ˩"]}, "version": "3.3.0", "architecture": "gmm-hmm", "train_date": "2026-06-05 18:45:43.976384", "training": {"audio_duration": 1577722.7508137012, "num_speakers": 1666, "num_utterances": 323695, "num_oovs": 0, "average_log_likelihood": -47.975523773700836}, "dictionaries": {"names": ["swedish_mfa"], "default": "swedish_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": 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": 0.01, "duration_information": {"a": [0.08280315899091796, 0.0489010840873834], "a˥˧": [0.09498519226153754, 0.027190369133631175], "a˥˩": [0.0813646757578761, 0.04247027996481302], "a˧˩": [0.09263559485009389, 0.037592890356094324], "a˩": [0.06771590378925656, 0.03154074637624819], "b": [0.06864728239188851, 0.02949106211126557], "d̪": [0.05458227605883203, 0.028546598388962265], "eː": [0.11123516835761695, 0.0787735745052711], "eː˥˧": [0.09492401552236551, 0.038901302672490666], "f": [0.10268717523566108, 0.04228712892427567], "n̪": [0.07043828365385059, 0.03540157212007017], "uː˥˩": [0.10002479208402397, 0.04541207025352603], "uː˧˩": [0.12360034929713716, 0.04738282133836677], "yː": [0.1528007793228538, 0.05912591448534212], "yː˥˧": [0.10826848532361898, 0.03474087833046437], "yː˥˩": [0.10080680421962859, 0.05270740743615457], "yː˧˩": [0.13840392107286778, 0.04768002030098198], "yː˩": [0.15454542636871338, 0.02252268374116977], "øː": [0.09093265075716794, 0.06069974916334533], "øː˥˧": [0.09154298741022819, 0.022572752935038035], "øː˥˩": [0.06753073932796978, 0.041441468004131496], "øː˧˩": [0.1132376381155395, 0.04848029003908521], "øː˩": [0.1616667111714681, 0.07194903824557486], "ɔ˥˩": [0.07549168152323192, 0.03485537740738443], "ɔ˧˩": [0.10860275912957877, 0.04350968149083742], "ɔ˩": [0.0519312124246012, 0.02347131141314132], "ɕ": [0.12186610340856269, 0.042206736462705], "ɖ": [0.06769117796047223, 0.02790413078339694], "ɛ": [0.07635263028950101, 0.047835617070471646], "ɛː": [0.08795343330158474, 0.06179667652525471], "ɛː˥˧": [0.15345381615232112, 0.0463071843098157], "ɛː˥˩": [0.11138461759457222, 0.03633791199324972], "ɪ˥˩": [0.05450215319622211, 0.034187967357625415], "ɪ˧˩": [0.07842717312119286, 0.035863700218323954], "ɪ˩": [0.06988674994570752, 0.04813044325702807], "ɭ": [0.06923271326903381, 0.021518884185336744], "ɳ": [0.055613710143696725, 0.020216412818282486], "ɵ": [0.07843845185306064, 0.0442074806890018], "ɵ˥˧": [0.08544381271452593, 0.033611182777371], "ɵ˥˩": [0.07137882608501803, 0.02849372561343338], "eː˥˩": [0.08371314899142519, 0.036629594905425576], "eː˧˩": [0.11414658415588073, 0.03906851165286469], "h": [0.06919106384015616, 0.061736848676983445], "iː": [0.09565896334929194, 0.07061109143359036], "iː˥˧": [0.08977419552543471, 0.042149063794138596], "iː˥˩": [0.08477387183598215, 0.0410116848136594], "iː˧˩": [0.08465643267534874, 0.044213610161323566], "j": [0.07302557778768419, 0.04682023120407291], "k": [0.090904468931234, 0.04364575591030399], "kʰ": [0.09750878627380317, 0.034392123282433434], "l̪": [0.06744228290575725, 0.032374167115637335], "m": [0.07935008944528238, 0.03644691362582899], "oː": [0.11122630756061459, 0.07767261851339037], "oː˥˧": [0.11687037964110021, 0.04027042029586516], "oː˥˩": [0.116965981243419, 0.05017590513680705], "oː˧˩": [0.09731880025096386, 0.047269883831279357], "p": [0.09805659043253086, 0.040718991445319416], "pʰ": [0.0836617017979753, 0.029540038430393798], "r": [0.0473404578058623, 0.035971290631263794], "s̪": [0.10323172521165126, 0.04592388476067151], "t̪": [0.092146587834328, 0.04974416311605307], "t̪ʰ": [0.10932540625860561, 0.04842898756057829], "uː": [0.1028246141361947, 0.05095004017452343], "uː˥˧": [0.12580356427601405, 0.05358565351046536], "ŋ": [0.08808383252872097, 0.041899476093876495], "œ": [0.07707062207479747, 0.04455445171036773], "œ˥˩": [0.08182754121155045, 0.037352371418040764], "œ˧˩": [0.07358866244729365, 0.029984494023321928], "ɑː": [0.0849851070960459, 0.05199870502385306], "ɑː˥˧": [0.1388103516689873, 0.041137080287726446], "ɑː˥˩": [0.09556378527879968, 0.04250631025888545], "ɑː˧˩": [0.09512464721846446, 0.05671810636122074], "ɔ": [0.07658918835239237, 0.0527828566990593], "ɔ˥˧": [0.11285281693562865, 0.04887872121388967], "ɛː˧˩": [0.13262475754346648, 0.04488943494196545], "ɛ˥˧": [0.09975315121844673, 0.03473530662770406], "ɛ˥˩": [0.05784153689868143, 0.03165112902309909], "ɛ˧˩": [0.08068004685956279, 0.03058516439426841], "ɛ˩": [0.05483174615839055, 0.027146468258551198], "ɡ": [0.06483792616930159, 0.03964759960577989], "ɧ": [0.09051084235398214, 0.05022311347095578], "ɪ": [0.06743256272004572, 0.03731417282422876], "ɪ˥˧": [0.058234578284559975, 0.021724184284264397], "ɵ˧˩": [0.08078403424455073, 0.032992610470982925], "ɵ˩": [0.06454546885056929, 0.018534854451522215], "ʂ": [0.09704975389131991, 0.04359919805658381], "ʈ": [0.11454956713243215, 0.052726164905195036], "ʈʰ": [0.12469646405038158, 0.04545789387412125], "ʉː": [0.12858960332873826, 0.07843654204609928], "ʉː˥˧": [0.11057485445530829, 0.030869180996702307], "ʉː˥˩": [0.09157404929293432, 0.040247520317901325], "ʉː˧˩": [0.11522989180555565, 0.045162071144661975], "ʊ": [0.06407294428318039, 0.048292729128810774], "ʊ˥˩": [0.1034029492472255, 0.059456399597716536], "ʊ˧˩": [0.08922644527492177, 0.04847575175926502], "ʊ˩": [0.0869444575574663, 0.06117043039095975], "ʋ": [0.060997344537823024, 0.028689991296601273], "ʏ": [0.08335896325231075, 0.036403501885405344], "ʏ˥˧": [0.07094592782291206, 0.021207991213027733], "ʏ˥˩": [0.1242220099499375, 0.07518961095303324], "ʏ˧˩": [0.07797870797759614, 0.03024191284897884], "ʏ˩": [0.09528248331977823, 0.05055560232413237]}}
 
1
+ {"phones": ["a", "a˥˧", "a˥˩", "a˧˩", "a˩", "b", "d̪", "eː", "eː˥˧", "eː˥˩", "eː˧˩", "eː˩", "f", "h", "iː", "iː˥˧", "iː˥˩", "iː˧˩", "j", "k", "kʰ", "l̪", "m", "n̪", "oː", "oː˥˧", "oː˥˩", "oː˧˩", "oː˩", "p", "pʰ", "r", "s̪", "t̪", "t̪ʰ", "uː", "uː˥˧", "uː˥˩", "uː˧˩", "yː", "yː˥˧", "yː˥˩", "yː˧˩", "yː˩", "øː", "øː˥˧", "øː˥˩", "øː˧˩", "øː˩", "ŋ", "œ", "œ˥˩", "œ˧˩", "ɑː", "ɑː˥˧", "ɑː˥˩", "ɑː˧˩", "ɑː˩", "ɔ", "ɔ˥˧", "ɔ˥˩", "ɔ˧˩", "ɔ˩", "ɕ", "ɖ", "ɛ", "ɛː", "ɛː˥˧", "ɛː˥˩", "ɛː˧˩", "ɛ˥˧", "ɛ˥˩", "ɛ˧˩", "ɛ˩", "ɡ", "ɧ", "ɪ", "ɪ˥˧", "ɪ˥˩", "ɪ˧˩", "ɪ˩", "ɭ", "ɳ", "ɵ", "ɵ˥˧", "ɵ˥˩", "ɵ˧˩", "ɵ˩", "ʂ", "ʈ", "ʈʰ", "ʉː", "ʉː˥˧", "ʉː˥˩", "ʉː˧˩", "ʊ", "ʊ˥˩", "ʊ˧˩", "ʊ˩", "ʋ", "ʏ", "ʏ˥˧", "ʏ˥˩", "ʏ˧˩", "ʏ˩"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "a˥˧": 4, "a˥˩": 5, "a˧˩": 6, "a˩": 7, "b": 8, "d̪": 9, "eː": 10, "eː˥˧": 11, "eː˥˩": 12, "eː˧˩": 13, "eː˩": 14, "f": 15, "h": 16, "iː": 17, "iː˥˧": 18, "iː˥˩": 19, "iː˧˩": 20, "j": 21, "k": 22, "kʰ": 23, "l̪": 24, "m": 25, "n̪": 26, "oː": 27, "oː˥˧": 28, "oː˥˩": 29, "oː˧˩": 30, "oː˩": 31, "p": 32, "pʰ": 33, "r": 34, "s̪": 35, "t̪": 36, "t̪ʰ": 37, "uː": 38, "uː˥˧": 39, "uː˥˩": 40, "uː˧˩": 41, "yː": 42, "yː˥˧": 43, "yː˥˩": 44, "yː˧˩": 45, "yː˩": 46, "øː": 47, "øː˥˧": 48, "øː˥˩": 49, "øː˧˩": 50, "øː˩": 51, "ŋ": 52, "œ": 53, "œ˥˩": 54, "œ˧˩": 55, "ɑː": 56, "ɑː˥˧": 57, "ɑː˥˩": 58, "ɑː˧˩": 59, "ɑː˩": 60, "ɔ": 61, "ɔ˥˧": 62, "ɔ˥˩": 63, "ɔ˧˩": 64, "ɔ˩": 65, "ɕ": 66, "ɖ": 67, "ɛ": 68, "ɛː": 69, "ɛː˥˧": 70, "ɛː˥˩": 71, "ɛː˧˩": 72, "ɛ˥˧": 73, "ɛ˥˩": 74, "ɛ˧˩": 75, "ɛ˩": 76, "ɡ": 77, "ɧ": 78, "ɪ": 79, "ɪ˥˧": 80, "ɪ˥˩": 81, "ɪ˧˩": 82, "ɪ˩": 83, "ɭ": 84, "ɳ": 85, "ɵ": 86, "ɵ˥˧": 87, "ɵ˥˩": 88, "ɵ˧˩": 89, "ɵ˩": 90, "ʂ": 91, "ʈ": 92, "ʈʰ": 93, "ʉː": 94, "ʉː˥˧": 95, "ʉː˥˩": 96, "ʉː˧˩": 97, "ʊ": 98, "ʊ˥˩": 99, "ʊ˧˩": 100, "ʊ˩": 101, "ʋ": 102, "ʏ": 103, "ʏ˥˧": 104, "ʏ˥˩": 105, "ʏ˧˩": 106, "ʏ˩": 107}, "phone_groups": {"0": ["b"], "1": ["d̪"], "2": ["f"], "3": ["h"], "4": ["j"], "5": ["k", "kʰ"], "6": ["l̪"], "7": ["m"], "8": ["n̪"], "9": ["p", "pʰ"], "10": ["r"], "11": ["s̪"], "12": ["t̪", "t̪ʰ"], "13": ["ŋ"], "14": ["ɕ"], "15": ["ɖ"], "16": ["ɡ"], "17": ["ɧ"], "18": ["ɭ"], "19": ["ɳ"], "20": ["ʂ"], "21": ["ʈ", "ʈʰ"], "22": ["ʋ"], "23": ["a", "a˥˧", "a˥˩", "a˧˩", "a˩"], "24": ["eː", "eː˥˧", "eː˥˩", "eː˧˩", "eː˩"], "25": ["iː", "iː˥˧", "iː˥˩", "iː˧˩"], "26": ["oː", "oː˥˧", "oː˥˩", "oː˧˩", "oː˩"], "27": ["uː", "uː˥˧", "uː˥˩", "uː˧˩"], "28": ["yː", "yː˥˧", "yː˥˩", "yː˧˩", "yː˩"], "29": ["øː", "øː˥˧", "øː˥˩", "øː˧˩", "øː˩"], "30": ["œ", "œ˥˩", "œ˧˩"], "31": ["ɑː", "ɑː˥˧", "ɑː˥˩", "ɑː˧˩", "ɑː˩"], "32": ["ɔ", "ɔ˥˧", "ɔ˥˩", "ɔ˧˩", "ɔ˩"], "33": ["ɛ", "ɛː", "ɛː˥˧", "ɛː˥˩", "ɛː˧˩", "ɛ˥˧", "ɛ˥˩", "ɛ˧˩", "ɛ˩"], "34": ["ɪ", "ɪ˥˧", "ɪ˥˩", "ɪ˧˩", "ɪ˩"], "35": ["ɵ", "ɵ˥˧", "ɵ˥˩", "ɵ˧˩", "ɵ˩"], "36": ["ʉː", "ʉː˥˧", "ʉː˥˩", "ʉː˧˩"], "37": ["ʊ", "ʊ˥˩", "ʊ˧˩", "ʊ˩"], "38": ["ʏ", "ʏ˥˧", "ʏ˥˩", "ʏ˧˩", "ʏ˩"]}, "version": "3.4.3", "architecture": "gmm-hmm", "train_date": "2026-10-13 06:06:34.346558", "training": {"audio_duration": 1574216.2098671582, "num_speakers": 1666, "num_utterances": 322556, "num_oovs": 0, "average_log_likelihood": -47.85601590944178}, "dictionaries": {"names": ["swedish_mfa"], "default": "swedish_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": 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": 0.01, "duration_information": {"a": [-2.5596181515296044, 0.506705337129811], "a˥˧": [-2.3812655877175506, 0.3183663284996819], "a˥˩": [-2.575236893614438, 0.46261674817125237], "a˧˩": [-2.4494162653417115, 0.41532661900633433], "a˩": [-2.7496737398423274, 0.45521521723260955], "b": [-2.75555949260343, 0.40184264768991906], "d̪": [-2.998999509605856, 0.43783343805144054], "eː": [-2.3790630444295577, 0.6875886719940698], "eː˥˧": [-2.3030697868646275, 0.5549152224384696], "eː˥˩": [-2.5116404473954845, 0.49097274061228613], "eː˧˩": [-2.185642176992375, 0.4103375324217422], "oː˥˧": [-2.103937125241358, 0.34603568001528495], "uː˥˧": [-2.2766856115463816, 0.5787190645791727], "uː˥˩": [-2.387151063242965, 0.49323839687275056], "uː˧˩": [-2.164543752635834, 0.42555880352151326], "yː": [-1.9663341735123077, 0.4204233864987463], "yː˥˧": [-2.265688506541544, 0.34691248757326265], "yː˥˩": [-2.4360281164790423, 0.541655648320528], "yː˧˩": [-2.049983265166856, 0.3909433114701744], "yː˩": [-1.8381065067256919, 0.10966245953902137], "œ˧˩": [-2.6428473322824124, 0.38685985335528], "ɑː": [-2.565851057408338, 0.5885785820929189], "ɑː˥˧": [-2.0250180571948735, 0.3393587089385598], "ɑː˥˩": [-2.3632686543418258, 0.4748481877779175], "ɑː˧˩": [-2.373601125654281, 0.5343145409501188], "ɔ": [-2.7077973937318207, 0.566063609151826], "ɔ˥˧": [-2.231507459857678, 0.4190313482825826], "ɛː˥˧": [-1.8751065033669845, 0.35361220527325615], "ɛː˥˩": [-2.195164300126775, 0.37680965696388224], "ɛː˧˩": [-2.0450032992667624, 0.3438167368840804], "ɛ˥˧": [-2.3915537864322847, 0.7127076516386955], "ɛ˥˩": [-2.9097781134419844, 0.4658582497146427], "ɛ˧˩": [-2.49411224160705, 0.3542525567591886], "f": [-2.3323068928979747, 0.38319576204415234], "h": [-2.927590127897013, 0.8009796266998375], "iː": [-2.551518955898495, 0.6482956919012915], "iː˥˧": [-2.538524395651082, 0.527398340563762], "iː˥˩": [-2.5761592554289, 0.5188350469822162], "iː˧˩": [-2.577957037941986, 0.5375893056461276], "j": [-2.784742268586358, 0.6068414485226289], "k": [-2.471376499330823, 0.4266073257403068], "kʰ": [-2.359517750380533, 0.3354188948694788], "l̪": [-2.813981302925895, 0.4331018724535039], "m": [-2.6294213851239165, 0.4236902348321442], "n̪": [-2.7805744588422514, 0.4545056785239573], "oː": [-2.438104649456344, 0.7216204482428245], "oː˥˩": [-2.1982560978148213, 0.46127476554730057], "oː˧˩": [-2.403569704066473, 0.507219523299957], "p": [-2.3917420122720783, 0.40481466707802766], "pʰ": [-2.518128056205839, 0.3528559290610195], "r": [-3.972731502184704, 0.8775159878134938], "s̪": [-2.3592773481444014, 0.42449735053357546], "t̪": [-2.524670762676599, 0.4986326589974803], "t̪ʰ": [-2.3009707835258837, 0.41172802597933617], "uː": [-2.3727026602565675, 0.592824960844594], "øː": [-2.5309600511925963, 0.6637101816200321], "øː˥˧": [-2.4281248444601533, 0.2649638560523414], "øː˥˩": [-2.7743660571153788, 0.5829568673753133], "øː˧˩": [-2.162034614645093, 0.45455531801605514], "øː˩": [-1.7513098758836136, 0.2062664883487888], "ŋ": [-2.535798673178827, 0.4689452678529025], "œ": [-2.6407321282437572, 0.5527954917418437], "œ˥˩": [-2.5974136420021448, 0.4558954406371657], "ɔ˥˩": [-2.605697330261033, 0.4614404998263791], "ɔ˧˩": [-2.2924192404317973, 0.42882332730350353], "ɔ˩": [-3.0146773028035763, 0.3904932545930481], "ɕ": [-2.230642326818172, 0.39030423281808385], "ɖ": [-2.7473509975297037, 0.3708500104118964], "ɛ": [-2.6875303313759393, 0.5672028851877093], "ɛː": [-2.6042853984426313, 0.6586766790567685], "ɛ˩": [-2.9495677409827192, 0.45046649698710306], "ɡ": [-2.9585852982106275, 0.7824047197617747], "ɧ": [-2.5343366399354665, 0.5796198320322083], "ɪ": [-2.803277465654522, 0.4921791494047247], "ɪ˥˧": [-2.866369051567273, 0.33936667397690995], "ɪ˥˩": [-2.9818363782672543, 0.4551292172926707], "ɪ˧˩": [-2.6338504322107354, 0.4574836571423182], "ɪ˩": [-2.802194639657845, 0.46103158227645596], "ɭ": [-2.8131292753771793, 0.35158908586654014], "ɳ": [-3.0025781410820884, 0.33037295744100154], "ɵ": [-2.6921951135802638, 0.5215944321242446], "ɵ˥˧": [-2.5206449905760966, 0.44537540157168837], "ɵ˥˩": [-2.7124465470402366, 0.37962112124697245], "ɵ˧˩": [-2.610527193182997, 0.4161528085703105], "ɵ˩": [-2.7904726830169766, 0.34567054643559914], "ʂ": [-2.4207615274711642, 0.4554724871351741], "ʈ": [-2.2754956193425615, 0.467985116420842], "ʈʰ": [-2.1541905307206415, 0.39919601004011657], "ʉː": [-2.2367665199261553, 0.6542181487040845], "ʉː˥˧": [-2.215226656871283, 0.30046533938597453], "ʉː˥˩": [-2.3770370416829514, 0.40013530399844394], "ʉː˧˩": [-2.23803540643036, 0.4462764810306725], "ʊ": [-3.0339663507017, 0.8656501281639656], "ʊ˥˩": [-2.4223369307415767, 0.5948987780709272], "ʊ˧˩": [-2.4916939341129902, 0.4956099887054715], "ʊ˩": [-2.7291402198310046, 0.5997142457067763], "ʋ": [-2.862165854981467, 0.43979825797447875], "ʏ": [-2.537977763335141, 0.40989647014826347], "ʏ˥˧": [-2.69336959885978, 0.32304209092693625], "ʏ˥˩": [-2.2443800693709055, 0.6099203401843656], "ʏ˧˩": [-2.5732039500276405, 0.34624653878147654], "ʏ˩": [-2.4309458883967134, 0.5223350040192699]}}
acoustic/tree CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b2a30b62509c9581bcfebe731294f3d7e4ba958b8c46e2279b396230a9bbc33
3
- size 429623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c19eda23acf565613ed8e3d6fb03e0a695f6bd8bc9ac350ad812d689ac496c16
3
+ size 441819
dictionary/rules.yaml CHANGED
@@ -1,19 +1,19 @@
1
  dialects:
2
  us:
3
  - following_context: $
4
- non_silence_before_correction: 0.0
5
  preceding_context: ''
6
- probability: 0.49
7
  replacement: t̪
8
  segment: k t̪
9
  silence_after_probability: 0.21
10
- silence_before_correction: 0.02
11
  - following_context: ''
12
- non_silence_before_correction: -0.02
13
  preceding_context: ''
14
- probability: 0.45
15
  replacement: r l̪
16
  segment: ɭ
17
- silence_after_probability: 0.53
18
- silence_before_correction: 0.23
19
  rules: []
 
1
  dialects:
2
  us:
3
  - following_context: $
4
+ non_silence_before_correction: -0.01
5
  preceding_context: ''
6
+ probability: 0.48
7
  replacement: t̪
8
  segment: k t̪
9
  silence_after_probability: 0.21
10
+ silence_before_correction: 0.04
11
  - following_context: ''
12
+ non_silence_before_correction: -0.03
13
  preceding_context: ''
14
+ probability: 0.42
15
  replacement: r l̪
16
  segment: ɭ
17
+ silence_after_probability: 0.64
18
+ silence_before_correction: 0.26
19
  rules: []
dictionary/swedish_mfa.dict CHANGED
The diff for this file is too large to render. See raw diff
 
g2p/swedish_mfa/meta.json CHANGED
@@ -1 +1 @@
1
- {"version": "3.2.0", "architecture": "phonetisaurus", "train_date": "2026-06-04 13:42:51.342685", "phones": ["a\u02e5\u02e7", "\u026d", "o\u02d0\u02e5\u02e7", "\u025b\u02e9", "i\u02d0", "j", "\u028f\u02e9", "s\u032a", "\u0275", "y\u02d0\u02e7\u02e9", "k\u02b0", "\u026a\u02e9", "\u028f", "e\u02d0\u02e9", "u\u02d0\u02e5\u02e7", "\u025b", "u\u02d0\u02e5\u02e9", "\u0251\u02d0\u02e7\u02e9", "\u0254\u02e7\u02e9", "\u0289\u02d0\u02e5\u02e7", "e\u02d0\u02e7\u02e9", "\u0254\u02e5\u02e9", "\u0256", "y\u02d0\u02e5\u02e7", "\u028b", "r", "p", "\u0275\u02e7\u02e9", "\u025b\u02d0", "\u014b", "\u0254", "\u0275\u02e5\u02e9", "\u0282", "o\u02d0", "\u0267", "o\u02d0\u02e9", "i\u02d0\u02e5\u02e9", "\u00f8\u02d0\u02e5\u02e9", "\u025b\u02d0\u02e5\u02e9", "\u025b\u02d0\u02e7\u02e9", "\u0288", "f", "\u00f8\u02d0", "\u025b\u02d0\u02e5\u02e7", "y\u02d0\u02e9", "\u00f8\u02d0\u02e9", "\u028a\u02e9", "\u025b\u02e7\u02e9", "b", "\u025b\u02e5\u02e9", "\u0261", "t\u032a", "\u0289\u02d0", "e\u02d0\u02e5\u02e9", "\u0255", "\u028f\u02e7\u02e9", "\u0254\u02e9", "\u028a", "\u0251\u02d0\u02e9", "\u0254\u02e5\u02e7", "e\u02d0", "\u026a\u02e5\u02e7", "n\u032a", "\u00f8\u02d0\u02e5\u02e7", "o\u02d0\u02e5\u02e9", "a\u02e5\u02e9", "\u0275\u02e9", "\u026a\u02e7\u02e9", "k", "\u0153\u02e5\u02e9", "\u0273", "u\u02d0\u02e7\u02e9", "\u0153", "\u028a\u02e5\u02e9", "\u0289\u02d0\u02e7\u02e9", "i\u02d0\u02e7\u02e9", "d\u032a", "\u0251\u02d0\u02e5\u02e7", "p\u02b0", "\u026a", "\u0251\u02d0\u02e5\u02e9", "\u00f8\u02d0\u02e7\u02e9", "e\u02d0\u02e5\u02e7", "y\u02d0", "h", "\u0251\u02d0", "\u0289\u02d0\u02e5\u02e9", "\u028f\u02e5\u02e9", "l\u032a", "m", "t\u032a\u02b0", "\u0153\u02e7\u02e9", "y\u02d0\u02e5\u02e9", "\u0275\u02e5\u02e7", "i\u02d0\u02e5\u02e7", "\u028f\u02e5\u02e7", "u\u02d0", "a\u02e9", "\u026a\u02e5\u02e9", "\u028a\u02e7\u02e9", "o\u02d0\u02e7\u02e9", "\u0288\u02b0", "a\u02e7\u02e9", "a", "\u025b\u02e5\u02e7"], "graphemes": ["x", "n", "\u00f6", "\u00f4", "w", "j", "u", "t", "z", "h", "g", "s", "m", "q", "\u00e9", "l", "\u00e4", "k", "f", "c", "i", "o", "b", "e", "\u00e5", "r", "p", "y", "\u00f8", "v", "d", "a"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": false, "evaluation": {"num_words": 5949, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 53540, "num_graphemes": 32, "num_phones": 105}}
 
1
+ {"version": "3.2.0", "architecture": "phonetisaurus", "train_date": "2026-06-04 13:42:51.342685", "phones": ["\u0251\u02d0\u02e5\u02e9", "a\u02e5\u02e9", "e\u02d0\u02e9", "\u028f\u02e9", "\u0261", "k\u02b0", "\u026a\u02e5\u02e7", "u\u02d0\u02e5\u02e9", "\u0254\u02e5\u02e7", "\u025b\u02d0\u02e7\u02e9", "\u028f", "k", "\u028a\u02e5\u02e9", "\u0254\u02e9", "p\u02b0", "a\u02e7\u02e9", "o\u02d0\u02e5\u02e9", "\u026a\u02e5\u02e9", "u\u02d0", "\u00f8\u02d0\u02e9", "\u0251\u02d0", "\u028f\u02e5\u02e9", "\u00f8\u02d0\u02e5\u02e7", "o\u02d0\u02e7\u02e9", "\u025b\u02d0", "e\u02d0\u02e5\u02e7", "j", "\u0275\u02e5\u02e9", "\u0254\u02e5\u02e9", "\u025b\u02e5\u02e9", "t\u032a", "\u028b", "b", "\u0251\u02d0\u02e7\u02e9", "\u0289\u02d0", "\u0288\u02b0", "u\u02d0\u02e7\u02e9", "\u028f\u02e7\u02e9", "m", "\u0289\u02d0\u02e5\u02e7", "e\u02d0\u02e5\u02e9", "t\u032a\u02b0", "\u0275\u02e7\u02e9", "o\u02d0\u02e5\u02e7", "\u0282", "y\u02d0\u02e7\u02e9", "n\u032a", "\u0275", "p", "\u0251\u02d0\u02e5\u02e7", "r", "\u028a\u02e7\u02e9", "e\u02d0", "\u0254\u02e7\u02e9", "i\u02d0\u02e7\u02e9", "\u0275\u02e5\u02e7", "f", "\u025b\u02d0\u02e5\u02e7", "\u028a", "\u0254", "a", "\u025b\u02e5\u02e7", "\u025b\u02d0\u02e5\u02e9", "\u0255", "\u025b\u02e7\u02e9", "e\u02d0\u02e7\u02e9", "\u025b", "\u00f8\u02d0\u02e7\u02e9", "\u0289\u02d0\u02e5\u02e9", "y\u02d0\u02e5\u02e7", "\u0273", "i\u02d0\u02e5\u02e7", "i\u02d0", "y\u02d0", "\u028a\u02e9", "\u026d", "\u0289\u02d0\u02e7\u02e9", "a\u02e5\u02e7", "o\u02d0", "y\u02d0\u02e5\u02e9", "\u00f8\u02d0\u02e5\u02e9", "h", "\u0288", "\u0251\u02d0\u02e9", "l\u032a", "i\u02d0\u02e5\u02e9", "\u0275\u02e9", "\u028f\u02e5\u02e7", "u\u02d0\u02e5\u02e7", "\u026a\u02e7\u02e9", "\u0256", "a\u02e9", "\u0153", "\u0267", "y\u02d0\u02e9", "\u0153\u02e5\u02e9", "s\u032a", "o\u02d0\u02e9", "\u026a", "\u0153\u02e7\u02e9", "\u014b", "\u00f8\u02d0", "\u025b\u02e9", "\u026a\u02e9", "d\u032a"], "graphemes": ["i", "\u00f6", "f", "j", "y", "a", "\u00f8", "c", "k", "e", "v", "b", "z", "w", "\u00e4", "s", "q", "x", "m", "\u00e5", "u", "o", "d", "t", "\u00e9", "p", "n", "r", "l", "g", "h", "\u00f4"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": false, "evaluation": {"num_words": 5949, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 53540, "num_graphemes": 32, "num_phones": 105}}