czech_mfa / acoustic /meta.json
mmcauliffe's picture
Upload folder using huggingface_hub
97e2441 verified
Raw
History Blame Contribute Delete
5.25 kB
{"phones": ["a", "aw", "aː", "b", "c", "d", "dz", "dʒ", "ew", "f", "iː", "j", "k", "l", "l̩", "m", "m̩", "n", "n̩", "o", "ow", "oː", "p", "r", "r̝", "r̝̊", "r̩", "s", "t", "ts", "tʃ", "u", "uː", "v", "x", "z", "ŋ", "ə", "ɛ", "ɛː", "ɟ", "ɡ", "ɦ", "ɪ", "ɲ", "ʃ", "ʒ", "ʔ"], "phone_mapping": {"<eps>": 0, "sil": 1, "spn": 2, "a": 3, "aw": 4, "aː": 5, "b": 6, "c": 7, "d": 8, "dz": 9, "dʒ": 10, "ew": 11, "f": 12, "iː": 13, "j": 14, "k": 15, "l": 16, "l̩": 17, "m": 18, "m̩": 19, "n": 20, "n̩": 21, "o": 22, "ow": 23, "oː": 24, "p": 25, "r": 26, "r̝": 27, "r̝̊": 28, "r̩": 29, "s": 30, "t": 31, "ts": 32, "tʃ": 33, "u": 34, "uː": 35, "v": 36, "x": 37, "z": 38, "ŋ": 39, "ə": 40, "ɛ": 41, "ɛː": 42, "ɟ": 43, "ɡ": 44, "ɦ": 45, "ɪ": 46, "ɲ": 47, "ʃ": 48, "ʒ": 49, "ʔ": 50}, "phone_groups": {"0": ["a", "aː"], "1": ["aw"], "2": ["b"], "3": ["c"], "4": ["d"], "5": ["dz"], "6": ["dʒ"], "7": ["ew"], "8": ["f"], "9": ["iː"], "10": ["j"], "11": ["k"], "12": ["l", "l̩"], "13": ["m", "m̩"], "14": ["n", "n̩"], "15": ["o", "oː"], "16": ["ow"], "17": ["p"], "18": ["r", "r̩"], "19": ["r̝"], "20": ["r̝̊"], "21": ["s"], "22": ["t"], "23": ["ts"], "24": ["tʃ"], "25": ["u", "uː"], "26": ["v"], "27": ["x"], "28": ["z"], "29": ["ŋ"], "30": ["ə"], "31": ["ɛ", "ɛː"], "32": ["ɟ"], "33": ["ɡ"], "34": ["ɦ"], "35": ["ɪ"], "36": ["ɲ"], "37": ["ʃ"], "38": ["ʒ"], "39": ["ʔ"]}, "version": "3.3.0", "architecture": "gmm-hmm", "train_date": "2026-05-18 17:43:38.797496", "training": {"audio_duration": 2237070.332494098, "num_speakers": 1597, "num_utterances": 328025, "num_oovs": 0, "average_log_likelihood": -52.41157951856638}, "dictionaries": {"names": ["czech_mfa"], "default": "czech_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": 0.21, "initial_silence_probability": 0.21, "final_silence_correction": 0.99, "final_non_silence_correction": 0.54, "duration_information": {"a": [0.0694119984918035, 0.05687721664773137], "aː": [0.12318409783799074, 0.0532980450296512], "aw": [0.1547737676844796, 0.045701465434459486], "b": [0.06943699962381301, 0.024620615812859546], "c": [0.0872660962912477, 0.03194689975070712], "d": [0.057514645204663324, 0.02332767941120894], "dz": [0.027938844526515287, 0.037887970791520904], "dʒ": [0.10373448311014379, 0.04808320628703324], "ə": [0.14528910652581664, 0.16472318379415277], "ew": [0.1612995678268291, 0.05156302905694492], "ɛ": [0.06466455502162013, 0.0443164834718277], "ɛː": [0.10533525608939585, 0.06141819990407253], "f": [0.08131461762305821, 0.04069141504474595], "ɡ": [0.0610591348972435, 0.025699816504368877], "ɦ": [0.06574266355153469, 0.03149671087994363], "ɪ": [0.07005048125544518, 0.05060367622566219], "iː": [0.08188866525747834, 0.05708570406777732], "j": [0.06281697194975004, 0.037541182495436067], "ɟ": [0.07378784849684036, 0.026579699417342503], "k": [0.08413140227930374, 0.03355208921256792], "l": [0.061010822640669087, 0.029336611371947492], "l̩": [0.09056163749948853, 0.0645437639012797], "m": [0.07289164182663962, 0.035664259648178334], "m̩": [0.05432589278360269, 0.043396361493581545], "n": [0.06141578360937811, 0.027022970687581645], "ɲ": [0.06260809185491846, 0.02894141301865896], "n̩": [0.08356275607128533, 0.1037205367437433], "ŋ": [0.07364233874871752, 0.02690682368991394], "o": [0.06722956315913234, 0.04745052331545804], "oː": [0.12283569888309534, 0.053375200894692366], "ow": [0.1193024867665086, 0.06637785089645407], "p": [0.07522328378948241, 0.029916255192130512], "r": [0.05273818199392348, 0.018545278454171428], "r̝": [0.06792206291906693, 0.02301689172765625], "r̩": [0.06915944612153128, 0.029330939454625688], "r̝̊": [0.0741687787201893, 0.02454241259074989], "s": [0.09741385082635462, 0.039772518489408035], "ʃ": [0.10527476584597698, 0.04682179675990852], "t": [0.07589008882591362, 0.03712281417521499], "ts": [0.11035858709133246, 0.04184482762922019], "tʃ": [0.1118578351334527, 0.03429920017851116], "u": [0.07286003140388334, 0.05252037454429164], "uː": [0.10497868361607936, 0.06602109305025367], "v": [0.05967067418005055, 0.022445601134499133], "x": [0.0897363666775142, 0.051427078733291866], "z": [0.07609630248127436, 0.029735881643480202], "ʒ": [0.08060116005330131, 0.031033640894308864], "ʔ": [0.04903541225171604, 0.02353890021762077]}}