swedish_mfa / acoustic /meta.json
mmcauliffe's picture
Upload folder using huggingface_hub
5e04933 verified
Raw
History Blame Contribute Delete
10.3 kB
{"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]}}