Upload tokenizer
Browse files- README.md +199 -0
- added_tokens.json +3 -0
- tokenizer.json +145 -109
- tokenizer_config.json +47 -3
- vocab.json +1 -1
README.md
ADDED
@@ -0,0 +1,199 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
tags: []
|
4 |
+
---
|
5 |
+
|
6 |
+
# Model Card for Model ID
|
7 |
+
|
8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
9 |
+
|
10 |
+
|
11 |
+
|
12 |
+
## Model Details
|
13 |
+
|
14 |
+
### Model Description
|
15 |
+
|
16 |
+
<!-- Provide a longer summary of what this model is. -->
|
17 |
+
|
18 |
+
This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
|
19 |
+
|
20 |
+
- **Developed by:** [More Information Needed]
|
21 |
+
- **Funded by [optional]:** [More Information Needed]
|
22 |
+
- **Shared by [optional]:** [More Information Needed]
|
23 |
+
- **Model type:** [More Information Needed]
|
24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
25 |
+
- **License:** [More Information Needed]
|
26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
27 |
+
|
28 |
+
### Model Sources [optional]
|
29 |
+
|
30 |
+
<!-- Provide the basic links for the model. -->
|
31 |
+
|
32 |
+
- **Repository:** [More Information Needed]
|
33 |
+
- **Paper [optional]:** [More Information Needed]
|
34 |
+
- **Demo [optional]:** [More Information Needed]
|
35 |
+
|
36 |
+
## Uses
|
37 |
+
|
38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
39 |
+
|
40 |
+
### Direct Use
|
41 |
+
|
42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
43 |
+
|
44 |
+
[More Information Needed]
|
45 |
+
|
46 |
+
### Downstream Use [optional]
|
47 |
+
|
48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
49 |
+
|
50 |
+
[More Information Needed]
|
51 |
+
|
52 |
+
### Out-of-Scope Use
|
53 |
+
|
54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
55 |
+
|
56 |
+
[More Information Needed]
|
57 |
+
|
58 |
+
## Bias, Risks, and Limitations
|
59 |
+
|
60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
61 |
+
|
62 |
+
[More Information Needed]
|
63 |
+
|
64 |
+
### Recommendations
|
65 |
+
|
66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
67 |
+
|
68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
69 |
+
|
70 |
+
## How to Get Started with the Model
|
71 |
+
|
72 |
+
Use the code below to get started with the model.
|
73 |
+
|
74 |
+
[More Information Needed]
|
75 |
+
|
76 |
+
## Training Details
|
77 |
+
|
78 |
+
### Training Data
|
79 |
+
|
80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
81 |
+
|
82 |
+
[More Information Needed]
|
83 |
+
|
84 |
+
### Training Procedure
|
85 |
+
|
86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
87 |
+
|
88 |
+
#### Preprocessing [optional]
|
89 |
+
|
90 |
+
[More Information Needed]
|
91 |
+
|
92 |
+
|
93 |
+
#### Training Hyperparameters
|
94 |
+
|
95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
96 |
+
|
97 |
+
#### Speeds, Sizes, Times [optional]
|
98 |
+
|
99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
100 |
+
|
101 |
+
[More Information Needed]
|
102 |
+
|
103 |
+
## Evaluation
|
104 |
+
|
105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
106 |
+
|
107 |
+
### Testing Data, Factors & Metrics
|
108 |
+
|
109 |
+
#### Testing Data
|
110 |
+
|
111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
112 |
+
|
113 |
+
[More Information Needed]
|
114 |
+
|
115 |
+
#### Factors
|
116 |
+
|
117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
118 |
+
|
119 |
+
[More Information Needed]
|
120 |
+
|
121 |
+
#### Metrics
|
122 |
+
|
123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
124 |
+
|
125 |
+
[More Information Needed]
|
126 |
+
|
127 |
+
### Results
|
128 |
+
|
129 |
+
[More Information Needed]
|
130 |
+
|
131 |
+
#### Summary
|
132 |
+
|
133 |
+
|
134 |
+
|
135 |
+
## Model Examination [optional]
|
136 |
+
|
137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
138 |
+
|
139 |
+
[More Information Needed]
|
140 |
+
|
141 |
+
## Environmental Impact
|
142 |
+
|
143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
144 |
+
|
145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
146 |
+
|
147 |
+
- **Hardware Type:** [More Information Needed]
|
148 |
+
- **Hours used:** [More Information Needed]
|
149 |
+
- **Cloud Provider:** [More Information Needed]
|
150 |
+
- **Compute Region:** [More Information Needed]
|
151 |
+
- **Carbon Emitted:** [More Information Needed]
|
152 |
+
|
153 |
+
## Technical Specifications [optional]
|
154 |
+
|
155 |
+
### Model Architecture and Objective
|
156 |
+
|
157 |
+
[More Information Needed]
|
158 |
+
|
159 |
+
### Compute Infrastructure
|
160 |
+
|
161 |
+
[More Information Needed]
|
162 |
+
|
163 |
+
#### Hardware
|
164 |
+
|
165 |
+
[More Information Needed]
|
166 |
+
|
167 |
+
#### Software
|
168 |
+
|
169 |
+
[More Information Needed]
|
170 |
+
|
171 |
+
## Citation [optional]
|
172 |
+
|
173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
174 |
+
|
175 |
+
**BibTeX:**
|
176 |
+
|
177 |
+
[More Information Needed]
|
178 |
+
|
179 |
+
**APA:**
|
180 |
+
|
181 |
+
[More Information Needed]
|
182 |
+
|
183 |
+
## Glossary [optional]
|
184 |
+
|
185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
186 |
+
|
187 |
+
[More Information Needed]
|
188 |
+
|
189 |
+
## More Information [optional]
|
190 |
+
|
191 |
+
[More Information Needed]
|
192 |
+
|
193 |
+
## Model Card Authors [optional]
|
194 |
+
|
195 |
+
[More Information Needed]
|
196 |
+
|
197 |
+
## Model Card Contact
|
198 |
+
|
199 |
+
[More Information Needed]
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 196
|
3 |
+
}
|
tokenizer.json
CHANGED
@@ -38,6 +38,15 @@
|
|
38 |
"rstrip": false,
|
39 |
"normalized": false,
|
40 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
41 |
}
|
42 |
],
|
43 |
"normalizer": {
|
@@ -116,61 +125,61 @@
|
|
116 |
"ɑ̃": 48,
|
117 |
"r": 49,
|
118 |
"x": 50,
|
119 |
-
"
|
120 |
-
"
|
121 |
"a": 53,
|
122 |
-
"
|
123 |
-
"
|
124 |
-
"
|
125 |
-
"
|
126 |
-
"
|
127 |
-
"
|
128 |
-
"
|
129 |
-
"
|
130 |
-
"
|
131 |
-
"
|
132 |
-
"
|
133 |
-
"
|
134 |
-
"
|
135 |
-
"
|
136 |
-
"
|
137 |
-
"
|
138 |
-
"
|
139 |
-
"
|
140 |
-
"
|
141 |
-
"
|
142 |
-
"
|
143 |
-
"
|
144 |
-
"
|
145 |
-
"
|
146 |
-
"
|
147 |
-
"
|
148 |
-
"
|
149 |
-
"
|
150 |
-
"
|
151 |
-
"
|
152 |
-
"
|
153 |
-
"
|
154 |
-
"
|
155 |
-
"
|
156 |
-
"
|
157 |
-
"
|
158 |
-
"
|
159 |
-
"
|
160 |
-
"
|
161 |
-
"
|
162 |
-
"
|
163 |
-
"
|
164 |
-
"
|
165 |
-
"
|
166 |
-
"
|
167 |
-
"
|
168 |
-
"
|
169 |
-
"
|
170 |
-
"
|
171 |
-
"
|
172 |
-
"
|
173 |
-
"
|
174 |
"tɕ": 106,
|
175 |
"ʈʂ": 107,
|
176 |
"ɹ̩": 108,
|
@@ -179,61 +188,88 @@
|
|
179 |
"ɻ": 111,
|
180 |
"ɥ": 112,
|
181 |
"tsʰ": 113,
|
182 |
-
"
|
183 |
-
"
|
184 |
-
"
|
185 |
-
"
|
186 |
-
"
|
187 |
-
"
|
188 |
-
"
|
189 |
-
"
|
190 |
-
"
|
191 |
-
"
|
192 |
-
"
|
193 |
-
"
|
194 |
-
"
|
195 |
-
"
|
196 |
-
"
|
197 |
-
"
|
198 |
-
"
|
199 |
-
"
|
200 |
-
"
|
201 |
-
"
|
202 |
-
"
|
203 |
-
"
|
204 |
-
"
|
205 |
-
"
|
206 |
-
"
|
207 |
-
"
|
208 |
-
"
|
209 |
-
"
|
210 |
-
"
|
211 |
-
"
|
212 |
-
"
|
213 |
-
"
|
214 |
-
"
|
215 |
-
"
|
216 |
-
"
|
217 |
-
"
|
218 |
-
"
|
219 |
-
"
|
220 |
-
"
|
221 |
-
"
|
222 |
-
"
|
223 |
-
"
|
224 |
-
"
|
225 |
-
"
|
226 |
-
"
|
227 |
-
"
|
228 |
-
"
|
229 |
-
"
|
230 |
-
"
|
231 |
-
"
|
232 |
-
"
|
233 |
-
"
|
234 |
-
"
|
235 |
-
"
|
236 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
237 |
},
|
238 |
"unk_token": "UNK"
|
239 |
}
|
|
|
38 |
"rstrip": false,
|
39 |
"normalized": false,
|
40 |
"special": true
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"id": 196,
|
44 |
+
"content": "<|endoftext|>",
|
45 |
+
"single_word": false,
|
46 |
+
"lstrip": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"special": true
|
50 |
}
|
51 |
],
|
52 |
"normalizer": {
|
|
|
125 |
"ɑ̃": 48,
|
126 |
"r": 49,
|
127 |
"x": 50,
|
128 |
+
"nʲ": 51,
|
129 |
+
"ɒ": 52,
|
130 |
"a": 53,
|
131 |
+
"ɑː": 54,
|
132 |
+
"ɔː": 55,
|
133 |
+
"əʊ": 56,
|
134 |
+
"ɐ": 57,
|
135 |
+
"eə": 58,
|
136 |
+
"ʊə": 59,
|
137 |
+
"n̩": 60,
|
138 |
+
"aː": 61,
|
139 |
+
"y": 62,
|
140 |
+
"ɛ̃": 63,
|
141 |
+
"ʁ": 64,
|
142 |
+
"e": 65,
|
143 |
+
"ɔ̃": 66,
|
144 |
+
"u": 67,
|
145 |
+
"o": 68,
|
146 |
+
"œ̃": 69,
|
147 |
+
"ø": 70,
|
148 |
+
"œ": 71,
|
149 |
+
"oː": 72,
|
150 |
+
"yː": 73,
|
151 |
+
"ɲ": 74,
|
152 |
+
"ts": 75,
|
153 |
+
"eː": 76,
|
154 |
+
"ʀ": 77,
|
155 |
+
"ç": 78,
|
156 |
+
"ɛɪ": 79,
|
157 |
+
"ʏ": 80,
|
158 |
+
"ɛː": 81,
|
159 |
+
"pf": 82,
|
160 |
+
"øː": 83,
|
161 |
+
"ã": 84,
|
162 |
+
"ɾ": 85,
|
163 |
+
"β": 86,
|
164 |
+
"ʎ": 87,
|
165 |
+
"ɣ": 88,
|
166 |
+
"ʝ": 89,
|
167 |
+
"oɪ": 90,
|
168 |
+
"eʊ": 91,
|
169 |
+
"pː": 92,
|
170 |
+
"ɟ": 93,
|
171 |
+
"ʋ": 94,
|
172 |
+
"ɪː": 95,
|
173 |
+
"ɵ": 96,
|
174 |
+
"œy": 97,
|
175 |
+
"tʲ": 98,
|
176 |
+
"au̯": 99,
|
177 |
+
"ʂ": 100,
|
178 |
+
"ɤ": 101,
|
179 |
+
"kʰ": 102,
|
180 |
+
"ʈʂʰ": 103,
|
181 |
+
"ɕ": 104,
|
182 |
+
"pʰ": 105,
|
183 |
"tɕ": 106,
|
184 |
"ʈʂ": 107,
|
185 |
"ɹ̩": 108,
|
|
|
188 |
"ɻ": 111,
|
189 |
"ɥ": 112,
|
190 |
"tsʰ": 113,
|
191 |
+
"ei̯": 114,
|
192 |
+
"ou̯": 115,
|
193 |
+
"ɻ̩": 116,
|
194 |
+
"ai̯": 117,
|
195 |
+
"ɯː": 118,
|
196 |
+
"ɯ": 119,
|
197 |
+
"pʲ": 120,
|
198 |
+
"ɸ": 121,
|
199 |
+
"rʲ": 122,
|
200 |
+
"kʲ": 123,
|
201 |
+
"bʲ": 124,
|
202 |
+
"mʲ": 125,
|
203 |
+
"kː": 126,
|
204 |
+
"æi": 127,
|
205 |
+
"yi": 128,
|
206 |
+
"ɵː": 129,
|
207 |
+
"tː": 130,
|
208 |
+
"æː": 131,
|
209 |
+
"dʑ": 132,
|
210 |
+
"l̩": 133,
|
211 |
+
"œː": 134,
|
212 |
+
"ʌː": 135,
|
213 |
+
"ɜ": 136,
|
214 |
+
"ʔ": 137,
|
215 |
+
"s̺": 138,
|
216 |
+
"ts̻": 139,
|
217 |
+
"s̻": 140,
|
218 |
+
"c": 141,
|
219 |
+
"ts̺": 142,
|
220 |
+
"tsː": 143,
|
221 |
+
"ɟː": 144,
|
222 |
+
"t̠ʃː": 145,
|
223 |
+
"ɡː": 146,
|
224 |
+
"dː": 147,
|
225 |
+
"cː": 148,
|
226 |
+
"bː": 149,
|
227 |
+
"dzː": 150,
|
228 |
+
"ɫ": 151,
|
229 |
+
"ʊː": 152,
|
230 |
+
"q": 153,
|
231 |
+
"øy": 154,
|
232 |
+
"χ": 155,
|
233 |
+
"i̯": 156,
|
234 |
+
"t̪": 157,
|
235 |
+
"d̪": 158,
|
236 |
+
"lʲ": 159,
|
237 |
+
"ɡʲ": 160,
|
238 |
+
"hʲ": 161,
|
239 |
+
"dʲ": 162,
|
240 |
+
"çʲ": 163,
|
241 |
+
"uə": 164,
|
242 |
+
"ŭ": 165,
|
243 |
+
"fʲ": 166,
|
244 |
+
"aɨ": 167,
|
245 |
+
"ɨ": 168,
|
246 |
+
"uɨ": 169,
|
247 |
+
"əɪ": 170,
|
248 |
+
"ɨː": 171,
|
249 |
+
"ɬ": 172,
|
250 |
+
"əɨ": 173,
|
251 |
+
"ɪu": 174,
|
252 |
+
"ʉ": 175,
|
253 |
+
"ʉː": 176,
|
254 |
+
"ɑɪ": 177,
|
255 |
+
"ʑ": 178,
|
256 |
+
"dz": 179,
|
257 |
+
"d̠ʒː": 180,
|
258 |
+
"ɐ̃": 181,
|
259 |
+
"ɛʊ": 182,
|
260 |
+
"ũ": 183,
|
261 |
+
"iʊ": 184,
|
262 |
+
"õ": 185,
|
263 |
+
"uɪ": 186,
|
264 |
+
"sʲ": 187,
|
265 |
+
"t̠ʃʲ": 188,
|
266 |
+
"ɔa": 189,
|
267 |
+
"ea": 190,
|
268 |
+
"iɪ": 191,
|
269 |
+
"tsʲ": 192,
|
270 |
+
"eo": 193,
|
271 |
+
"d̠ʒʲ": 194,
|
272 |
+
"ɾʲ": 195
|
273 |
},
|
274 |
"unk_token": "UNK"
|
275 |
}
|
tokenizer_config.json
CHANGED
@@ -1,8 +1,52 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
-
"
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
6 |
"tokenizer_class": "GPT2Tokenizer",
|
7 |
-
"unk_token": "
|
8 |
}
|
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"0": {
|
5 |
+
"content": "UNK",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"1": {
|
13 |
+
"content": "PAD",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"2": {
|
21 |
+
"content": "BOS",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
},
|
28 |
+
"3": {
|
29 |
+
"content": "EOS",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": true
|
35 |
+
},
|
36 |
+
"196": {
|
37 |
+
"content": "<|endoftext|>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": true
|
43 |
+
}
|
44 |
+
},
|
45 |
+
"bos_token": "BOS",
|
46 |
+
"clean_up_tokenization_spaces": true,
|
47 |
+
"eos_token": "EOS",
|
48 |
"model_max_length": 1000000000000000019884624838656,
|
49 |
+
"pad_token": "PAD",
|
50 |
"tokenizer_class": "GPT2Tokenizer",
|
51 |
+
"unk_token": "UNK"
|
52 |
}
|
vocab.json
CHANGED
@@ -1 +1 @@
|
|
1 |
-
{"UNK":0,"PAD":1,"BOS":2,"EOS":3,"WORD_BOUNDARY":4,"UTT_BOUNDARY":5,"s":6,"iː":7,"ð":8,"ɛ":9,"ɹ":10,"z":11,"ʌ":12,"f":13,"eɪ":14,"w":15,"ɪ":16,"ɡ":17,"l":18,"æ":19,"ɑ":20,"h":21,"ə":22,"ʊ":23,"k":24,"p":25,"uː":26,"b":27,"i":28,"t":29,"aɪ":30,"θ":31,"ŋ":32,"j":33,"ɔ":34,"m":35,"ɔɪ":36,"n":37,"d":38,"oʊ":39,"aʊ":40,"v":41,"ɜː":42,"t̠ʃ":43,"d̠ʒ":44,"ʃ":45,"iə":46,"ʒ":47,"ɑ̃":48,"r":49,"x":50,"
|
|
|
1 |
+
{"UNK":0,"PAD":1,"BOS":2,"EOS":3,"WORD_BOUNDARY":4,"UTT_BOUNDARY":5,"s":6,"iː":7,"ð":8,"ɛ":9,"ɹ":10,"z":11,"ʌ":12,"f":13,"eɪ":14,"w":15,"ɪ":16,"ɡ":17,"l":18,"æ":19,"ɑ":20,"h":21,"ə":22,"ʊ":23,"k":24,"p":25,"uː":26,"b":27,"i":28,"t":29,"aɪ":30,"θ":31,"ŋ":32,"j":33,"ɔ":34,"m":35,"ɔɪ":36,"n":37,"d":38,"oʊ":39,"aʊ":40,"v":41,"ɜː":42,"t̠ʃ":43,"d̠ʒ":44,"ʃ":45,"iə":46,"ʒ":47,"ɑ̃":48,"r":49,"x":50,"nʲ":51,"ɒ":52,"a":53,"ɑː":54,"ɔː":55,"əʊ":56,"ɐ":57,"eə":58,"ʊə":59,"n̩":60,"aː":61,"y":62,"ɛ̃":63,"ʁ":64,"e":65,"ɔ̃":66,"u":67,"o":68,"œ̃":69,"ø":70,"œ":71,"oː":72,"yː":73,"ɲ":74,"ts":75,"eː":76,"ʀ":77,"ç":78,"ɛɪ":79,"ʏ":80,"ɛː":81,"pf":82,"øː":83,"ã":84,"ɾ":85,"β":86,"ʎ":87,"ɣ":88,"ʝ":89,"oɪ":90,"eʊ":91,"pː":92,"ɟ":93,"ʋ":94,"ɪː":95,"ɵ":96,"œy":97,"tʲ":98,"au̯":99,"ʂ":100,"ɤ":101,"kʰ":102,"ʈʂʰ":103,"ɕ":104,"pʰ":105,"tɕ":106,"ʈʂ":107,"ɹ̩":108,"tɕʰ":109,"tʰ":110,"ɻ":111,"ɥ":112,"tsʰ":113,"ei̯":114,"ou̯":115,"ɻ̩":116,"ai̯":117,"ɯː":118,"ɯ":119,"pʲ":120,"ɸ":121,"rʲ":122,"kʲ":123,"bʲ":124,"mʲ":125,"kː":126,"æi":127,"yi":128,"ɵː":129,"tː":130,"æː":131,"dʑ":132,"l̩":133,"œː":134,"ʌː":135,"ɜ":136,"ʔ":137,"s̺":138,"ts̻":139,"s̻":140,"c":141,"ts̺":142,"tsː":143,"ɟː":144,"t̠ʃː":145,"ɡː":146,"dː":147,"cː":148,"bː":149,"dzː":150,"ɫ":151,"ʊː":152,"q":153,"øy":154,"χ":155,"i̯":156,"t̪":157,"d̪":158,"lʲ":159,"ɡʲ":160,"hʲ":161,"dʲ":162,"çʲ":163,"uə":164,"ŭ":165,"fʲ":166,"aɨ":167,"ɨ":168,"uɨ":169,"əɪ":170,"ɨː":171,"ɬ":172,"əɨ":173,"ɪu":174,"ʉ":175,"ʉː":176,"ɑɪ":177,"ʑ":178,"dz":179,"d̠ʒː":180,"ɐ̃":181,"ɛʊ":182,"ũ":183,"iʊ":184,"õ":185,"uɪ":186,"sʲ":187,"t̠ʃʲ":188,"ɔa":189,"ea":190,"iɪ":191,"tsʲ":192,"eo":193,"d̠ʒʲ":194,"ɾʲ":195}
|