mmcauliffe commited on
Commit
1aaa836
·
verified ·
1 Parent(s): 97e2441

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -109,9 +109,9 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
109
  | **Open** | | | a aː | | |
110
 
111
  ##### Diphthongs
112
- * aw
113
  * ow
114
  * ew
 
115
 
116
 
117
  ## Training Details
@@ -125,53 +125,49 @@ To get started, follow the instructions for [installing MFA](https://montreal-fo
125
  - **Source:** https://voice.mozilla.org/en/datasets
126
  - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
127
  - **Dialects:** N/A
128
- - **Number of hours:** 66.33
129
- - **Number of utterances:** 55,391
130
- - **Number of speakers:** 523
131
- - **Female speakers:** 183
132
- - **Male speakers:** 37
133
- - **Unknown speakers:** 322
134
-
135
 
136
  #### Czech Parliament Meetings
137
 
138
  - **Source:** https://lindat.mff.cuni.cz/repository/xmlui/handle/11858/00-097C-0000-0005-CF9C-4
139
  - **License:** [CC BY-NC-ND 3.0](https://creativecommons.org/licenses/by-nc-nd/3.0/)
140
  - **Dialects:** N/A
141
- - **Number of hours:** 88.81
142
- - **Number of utterances:** 51,494
143
- - **Number of speakers:** 67
144
  - **Female speakers:** 0
145
  - **Male speakers:** 0
146
  - **Unknown speakers:** 67
147
 
148
-
149
  #### GlobalPhone Czech
150
 
151
  - **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0196/
152
  - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
153
  - **Dialects:** N/A
154
- - **Number of hours:** 31.67
155
- - **Number of utterances:** 12,322
156
  - **Number of speakers:** 101
157
  - **Female speakers:** 45
158
  - **Male speakers:** 57
159
  - **Unknown speakers:** 0
160
 
161
-
162
  #### Large Corpus of Czech Parliament Plenary Hearings
163
 
164
  - **Source:** https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3126
165
  - **License:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)
166
  - **Dialects:** N/A
167
- - **Number of hours:** 450.95
168
- - **Number of utterances:** 194,181
169
- - **Number of speakers:** 84
170
  - **Female speakers:** 0
171
  - **Male speakers:** 0
172
  - **Unknown speakers:** 84
173
 
174
-
175
  ### Training Procedure
176
 
177
  <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
 
109
  | **Open** | | | a aː | | |
110
 
111
  ##### Diphthongs
 
112
  * ow
113
  * ew
114
+ * aw
115
 
116
 
117
  ## Training Details
 
125
  - **Source:** https://voice.mozilla.org/en/datasets
126
  - **License:** [CC-0](https://creativecommons.org/publicdomain/zero/1.0/)
127
  - **Dialects:** N/A
128
+ - **Number of hours:** 71.36
129
+ - **Number of utterances:** 60,276
130
+ - **Number of speakers:** 999
131
+ - **Female speakers:** 35
132
+ - **Male speakers:** 304
133
+ - **Unknown speakers:** 670
 
134
 
135
  #### Czech Parliament Meetings
136
 
137
  - **Source:** https://lindat.mff.cuni.cz/repository/xmlui/handle/11858/00-097C-0000-0005-CF9C-4
138
  - **License:** [CC BY-NC-ND 3.0](https://creativecommons.org/licenses/by-nc-nd/3.0/)
139
  - **Dialects:** N/A
140
+ - **Number of hours:** 80.59
141
+ - **Number of utterances:** 51,445
142
+ - **Number of speakers:** 198
143
  - **Female speakers:** 0
144
  - **Male speakers:** 0
145
  - **Unknown speakers:** 67
146
 
 
147
  #### GlobalPhone Czech
148
 
149
  - **Source:** https://catalogue.elra.info/en-us/repository/browse/ELRA-S0196/
150
  - **License:** [ELRA](https://www.elra.info/en/services-around-lrs/distribution/licensing/)
151
  - **Dialects:** N/A
152
+ - **Number of hours:** 31.65
153
+ - **Number of utterances:** 12,352
154
  - **Number of speakers:** 101
155
  - **Female speakers:** 45
156
  - **Male speakers:** 57
157
  - **Unknown speakers:** 0
158
 
 
159
  #### Large Corpus of Czech Parliament Plenary Hearings
160
 
161
  - **Source:** https://lindat.mff.cuni.cz/repository/xmlui/handle/11234/1-3126
162
  - **License:** [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)
163
  - **Dialects:** N/A
164
+ - **Number of hours:** 438.35
165
+ - **Number of utterances:** 204,411
166
+ - **Number of speakers:** 344
167
  - **Female speakers:** 0
168
  - **Male speakers:** 0
169
  - **Unknown speakers:** 84
170
 
 
171
  ### Training Procedure
172
 
173
  <!-- 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:fc35563c081b63755eeea861dae45a830f5a5145c73ce3715dca29d559388454
3
- size 50082737
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13102f8708a911d4befa4759272f40042e2d1215bea95b36364e41130aadac91
3
+ size 50080498
acoustic/final.mdl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05eb92ce9e0593e16bb0fd3fd48092dfa7c61045115f9698ce353806aee31f18
3
- size 50082737
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04418dd045f1f5cf65c5122a82b7664add311c24641cc196c49cb4d15d9a6a64
3
+ size 50080498
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", "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]}}
 
1
+ {"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": "3.4.3", "architecture": "gmm-hmm", "train_date": "2026-10-09 05:27:16.660822", "training": {"audio_duration": 2232620.159937846, "num_speakers": 1597, "num_utterances": 327084, "num_oovs": 0, "average_log_likelihood": -52.340404924621424}, "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": 0.57, "duration_information": {"a": [-2.8193848092964555, 0.5030860793221705], "aw": [-1.9058687368665967, 0.30679030426667175], "aː": [-2.170866517208258, 0.41171918130414886], "b": [-2.719864410037368, 0.3488078109263064], "c": [-2.5125444022552776, 0.36491438122606135], "d": [-2.939650138180784, 0.37527712721736417], "dz": [-2.545117439052222, 0.3908877854148026], "dʒ": [-2.379862936646152, 0.4529812485439085], "ew": [-1.8710607814891076, 0.33721105104151344], "f": [-2.602810283982693, 0.45552669253969624], "iː": [-2.6852324217770027, 0.5552634189965184], "j": [-2.9039420793237025, 0.5445582372904737], "k": [-2.5569698629959836, 0.38002587386248654], "l": [-2.8691713117037314, 0.3817738986898634], "l̩": [-2.5633676354776638, 0.5318775187333405], "m": [-2.703556572322657, 0.41198653138197394], "m̩": [-3.0506420626928556, 0.5444193618777741], "n": [-2.8584203843072564, 0.37788264511056086], "n̩": [-2.6292156092412124, 0.5056738861305238], "o": [-2.821809760509923, 0.4515621452218157], "ow": [-2.2429398328670245, 0.4794269535971944], "oː": [-2.181069490745467, 0.443336787562333], "p": [-2.6660011033942594, 0.3849627029955284], "r": [-2.9963133556199337, 0.3053609733647267], "r̝": [-2.746309590928616, 0.35066777161336543], "r̝̊": [-2.656614088432661, 0.322339482944551], "r̩": [-2.7589162336096997, 0.37456803282149603], "s": [-2.401645195909443, 0.39272196003277665], "t": [-2.673056634210402, 0.41810493108872904], "ts": [-2.269784852333614, 0.3824491297251477], "tʃ": [-2.2375056589913163, 0.31025737221157573], "u": [-2.792663012447272, 0.54684768017601], "uː": [-2.420589257706202, 0.5671872382062705], "v": [-2.8798890147087053, 0.35689339994228714], "x": [-2.559154525732009, 0.532053560772595], "z": [-2.6462112492267904, 0.371123443966969], "ŋ": [-2.666233283105511, 0.36316722377911553], "ə": [-2.505329106841459, 1.043065246322122], "ɛ": [-2.8754446436341907, 0.48337744401028837], "ɛː": [-2.3828202599435806, 0.5241173443652304], "ɟ": [-2.6679767883588554, 0.3771272999765758], "ɡ": [-2.8671022969800677, 0.41379466286098404], "ɦ": [-2.8312384712562846, 0.47796966191609497], "ɪ": [-2.828907300441165, 0.5273825642367318], "ɲ": [-2.8619399392243463, 0.443434695526496], "ʃ": [-2.346895293423586, 0.4387221396602243], "ʒ": [-2.5961585738333355, 0.3822744645603496], "ʔ": [-3.0639211183013515, 0.3957495430994786]}}
acoustic/tree CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:293acc082b8d0928b2873c6c2f9e94672efcbfdc6023d718385063e035dc8fde
3
- size 302617
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ceb91a89c17c80d3fba8fd70d7e675bdac31252e5f6cc62433224a9b687c9e0
3
+ size 303085
dictionary/czech_mfa.dict CHANGED
The diff for this file is too large to render. See raw diff
 
dictionary/rules.yaml CHANGED
@@ -1,75 +1,75 @@
1
  dialects:
2
  us:
3
  - following_context: '[vn]'
4
- non_silence_before_correction: -0.07
5
  preceding_context: ^
6
  probability: 0.01
7
  replacement: d ə
8
  segment: d
9
- silence_after_probability: 0.66
10
- silence_before_correction: 0.14
11
  - following_context: '[d]'
12
- non_silence_before_correction: -0.2
13
  preceding_context: ^
14
  probability: 0.04
15
  replacement: ɡ ə
16
  segment: ɡ
17
- silence_after_probability: 0.33
18
- silence_before_correction: 0.41
19
  - following_context: '[smd]'
20
- non_silence_before_correction: 0.05
21
  preceding_context: ^
22
  probability: 0.03
23
  replacement: ''
24
  segment: j
25
  silence_after_probability: 0.22
26
- silence_before_correction: -0.19
27
  - following_context: $
28
- non_silence_before_correction: 0.0
29
  preceding_context: ''
30
  probability: 0.01
31
  replacement: u
32
  segment: u j ɪ
33
- silence_after_probability: 0.23
34
- silence_before_correction: -0.02
35
  - following_context: n
36
- non_silence_before_correction: 0.03
37
  preceding_context: s
38
  probability: 0.01
39
  replacement: ''
40
  segment: t
41
- silence_after_probability: 0.76
42
- silence_before_correction: -0.12
43
  - following_context: $
44
- non_silence_before_correction: 0.05
45
  preceding_context: ''
46
  probability: 0.01
47
  replacement: ''
48
  segment: t
49
- silence_after_probability: 0.28
50
- silence_before_correction: -0.16
51
  - following_context: $
52
- non_silence_before_correction: 0.02
53
  preceding_context: ''
54
  probability: 0.01
55
  replacement: u j u
56
  segment: u j ɪ
57
- silence_after_probability: 1.0
58
- silence_before_correction: -0.08
59
  - following_context: $
60
- non_silence_before_correction: 0.08
61
  preceding_context: ''
62
  probability: 0.01
63
  replacement: j iː
64
  segment: j ɛ j iː
65
- silence_after_probability: 0.13
66
- silence_before_correction: -0.3
67
  - following_context: ''
68
- non_silence_before_correction: 0.14
69
  preceding_context: ''
70
  probability: 0.01
71
  replacement: j ɛː
72
  segment: j ɛ j ɛ
73
- silence_after_probability: 0.67
74
- silence_before_correction: -0.29
75
  rules: []
 
1
  dialects:
2
  us:
3
  - following_context: '[vn]'
4
+ non_silence_before_correction: -0.04
5
  preceding_context: ^
6
  probability: 0.01
7
  replacement: d ə
8
  segment: d
9
+ silence_after_probability: 0.59
10
+ silence_before_correction: 0.06
11
  - following_context: '[d]'
12
+ non_silence_before_correction: -0.22
13
  preceding_context: ^
14
  probability: 0.04
15
  replacement: ɡ ə
16
  segment: ɡ
17
+ silence_after_probability: 0.35
18
+ silence_before_correction: 0.45
19
  - following_context: '[smd]'
20
+ non_silence_before_correction: 0.06
21
  preceding_context: ^
22
  probability: 0.03
23
  replacement: ''
24
  segment: j
25
  silence_after_probability: 0.22
26
+ silence_before_correction: -0.21
27
  - following_context: $
28
+ non_silence_before_correction: 0.03
29
  preceding_context: ''
30
  probability: 0.01
31
  replacement: u
32
  segment: u j ɪ
33
+ silence_after_probability: 0.17
34
+ silence_before_correction: -0.1
35
  - following_context: n
36
+ non_silence_before_correction: 0.04
37
  preceding_context: s
38
  probability: 0.01
39
  replacement: ''
40
  segment: t
41
+ silence_after_probability: 0.78
42
+ silence_before_correction: -0.13
43
  - following_context: $
44
+ non_silence_before_correction: 0.06
45
  preceding_context: ''
46
  probability: 0.01
47
  replacement: ''
48
  segment: t
49
+ silence_after_probability: 0.24
50
+ silence_before_correction: -0.19
51
  - following_context: $
52
+ non_silence_before_correction: 0.01
53
  preceding_context: ''
54
  probability: 0.01
55
  replacement: u j u
56
  segment: u j ɪ
57
+ silence_after_probability: 0.92
58
+ silence_before_correction: -0.07
59
  - following_context: $
60
+ non_silence_before_correction: 0.18
61
  preceding_context: ''
62
  probability: 0.01
63
  replacement: j iː
64
  segment: j ɛ j iː
65
+ silence_after_probability: 0.15
66
+ silence_before_correction: -0.46
67
  - following_context: ''
68
+ non_silence_before_correction: 0.29
69
  preceding_context: ''
70
  probability: 0.01
71
  replacement: j ɛː
72
  segment: j ɛ j ɛ
73
+ silence_after_probability: 0.52
74
+ silence_before_correction: -0.54
75
  rules: []
g2p/czech_mfa/graphemes.txt CHANGED
@@ -508,11 +508,11 @@ y|n 506
508
  ó|d 507
509
  j|s 508
510
  ü 509
511
- é|z 510
512
- a|š 511
513
- p|s 512
514
- o|j 513
515
- l|n 514
516
  k|ř 515
517
  e|p 516
518
  y|z 517
 
508
  ó|d 507
509
  j|s 508
510
  ü 509
511
+ p|s 510
512
+ é|z 511
513
+ a|š 512
514
+ l|n 513
515
+ o|j 514
516
  k|ř 515
517
  e|p 516
518
  y|z 517
g2p/czech_mfa/meta.json CHANGED
@@ -1 +1 @@
1
- {"version": "3.3.0", "architecture": "phonetisaurus", "train_date": "2026-05-18 18:00:40.584951", "phones": ["a", "aw", "a\u02d0", "b", "c", "d", "dz", "d\u0292", "ew", "f", "i\u02d0", "j", "k", "l", "l\u0329", "m", "m\u0329", "n", "n\u0329", "o", "ow", "o\u02d0", "p", "r", "r\u031d", "r\u031d\u030a", "r\u0329", "s", "t", "ts", "t\u0283", "u", "u\u02d0", "v", "x", "z", "\u014b", "\u0259", "\u025b", "\u025b\u02d0", "\u025f", "\u0261", "\u0266", "\u026a", "\u0272", "\u0283", "\u0292", "\u0294"], "graphemes": ["t", "w", "\u00e9", "a", "m", "\u00f3", "q", "b", "d", "l", "x", "u", "n", "s", "-", "v", "\u010f", "j", "\u00fd", "\u00e1", "y", "p", "g", "\u010d", "\u00fa", "r", "o", "'", "\u011b", "f", "z", "\u00f6", "\u017e", "h", "c", "e", "\u00ed", "\u016f", "\u0161", "\u0159", "\u0165", "i", "\u00fc", "k", "\u0148"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": false, "evaluation": {"num_words": 12477, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 112295, "num_graphemes": 45, "num_phones": 48}}
 
1
+ {"version": "3.4.3", "architecture": "phonetisaurus", "train_date": "2026-10-09 05:50:38.788649", "phones": ["a", "aw", "a\u02d0", "b", "c", "d", "dz", "d\u0292", "ew", "f", "i\u02d0", "j", "k", "l", "l\u0329", "m", "m\u0329", "n", "n\u0329", "o", "ow", "o\u02d0", "p", "r", "r\u031d", "r\u031d\u030a", "r\u0329", "s", "t", "ts", "t\u0283", "u", "u\u02d0", "v", "x", "z", "\u014b", "\u0259", "\u025b", "\u025b\u02d0", "\u025f", "\u0261", "\u0266", "\u026a", "\u0272", "\u0283", "\u0292", "\u0294"], "graphemes": ["x", "z", "c", "m", "t", "j", "\u011b", "\u00fd", "-", "n", "k", "v", "'", "y", "\u00e1", "g", "b", "\u016f", "p", "\u0161", "\u00fc", "\u010f", "\u0159", "\u00fa", "\u00f3", "\u017e", "h", "w", "r", "o", "q", "s", "d", "\u00e9", "\u00ed", "e", "a", "l", "\u00f6", "f", "\u010d", "\u0148", "\u0165", "u", "i"], "grapheme_order": 2, "phone_order": 2, "sequence_separator": "|", "unicode_decomposition": false, "evaluation": {"num_words": 12477, "word_error_rate": null, "phone_error_rate": null}, "training": {"num_words": 112295, "num_graphemes": 45, "num_phones": 48}}
g2p/czech_mfa/model.fst CHANGED

Git LFS Details

  • SHA256: 6183d0bb599c2a434670f8dfeb6d242b4233457ff15761771dbbda3cb41ce9ae
  • Pointer size: 133 Bytes
  • Size of remote file: 34 MB

Git LFS Details

  • SHA256: 851eef69f91f195436f2c44ff9a4948c08afef9a347661c809f3eb4779d3c95a
  • Pointer size: 133 Bytes
  • Size of remote file: 34 MB