am_am_FONIPA.txt (20933B)
1 # © 2016 and later: Unicode, Inc. and others. 2 # License & terms of use: http://www.unicode.org/copyright.html 3 # Generated using tools/cldr/cldr-to-icu/ 4 # 5 # File: am_am_FONIPA.txt 6 # Generated from CLDR 7 # 8 9 # Transforms Amharic (am) to Amharic in phonemic IPA transcription (am_FONIPA). 10 # 11 # Long vowels, long/geminated consonants: 12 # In the direction from am_FONIPA to am, we emit Ethiopic gemination 13 # and vowel length markers (U+135D, U+135E, U+135F) although 14 # they are rarely written in Amharic text. Exceptions include 15 # school books and textbooks for non-native speakers. 16 # Clients who do not want these markers can easily strip them off 17 # in a post-processing step. 18 # 19 # Labialization: 20 # Amharic speakers will usually say ሟ as [mʷa] instead of [mwa]; 21 # labializing [m] instead of saying [m] followed by a separate [w]. 22 # Most Amharic consonants can get labialized. To keep the phonemic 23 # transcription simple, we emit /m/ + /w/; otherwise, our phoneme 24 # set would almost double, and it would include very unusual phonemes 25 # such as /ɲʷ/ or /t\u0361ʃʼʷ/. 26 # 27 # References: 28 # [1] The Ge’ez Frontier Foundation: “Principles and Specification 29 # for Mnemonic Ethiopic Keyboards.” Version of January 17, 2009; 30 # retrieved on November 4, 2014. 31 # http://keyboards.ethiopic.org/specification/GFF-MnemonicEthiopicKeyboardSpecification.pdf 32 # Other than most online sources, this report uses correct IPA notation 33 # with the exception of /j/, which it consistently (but wrongly) 34 # writes as */y/. 35 $IPA_VOWEL = [aeəiɨou]; 36 $IPA_CONSONANT = [mnɲɴ p{pʼ}bt{tʼ}dk{kʼ}ɡʔʕ fvs{sʼ}zʃʒxh lr {t\u0361ʃ}{t\u0361ʃʼ}{d\u0361ʒ}]; 37 # Some consonants have a special syllable when labialized, such as ፗ ↔ /pʷa/. 38 # Amharic restricts this mostly to /a/ syllables. While the Ethiopic script 39 # does offer labialized syllables for other vowels, these are typically 40 # not written in Amharic. 41 $LABIALIZABLE_BEFORE_A = [p{pʼ}t{tʼ} {t\u0361ʃ}{t\u0361ʃʼ}{d\u0361ʒ}{d\u0361ʒʼ} s{sʼ}zʃʒ fv r]; 42 ← [ ʼ \u0361 \u035C \u032F]; 43 ::(null); 44 # Appendix B of [1] transcribes ሀ as /hə/. However, according to 45 # an Amharic-speaking person, there is no /hə/ sequence 46 # in Amharic; instead, it gets pronounced as /ha/. 47 ሀ → ha; 48 ሀ ← hə; 49 ሁ ↔ hu; 50 ሂ ↔ hi; 51 ሃ ↔ ha; 52 ሄ ↔ he; 53 ህ ↔ hɨ; 54 ሆ ↔ ho; 55 ሇ → ho; # Dizi, Me’en, Mursi, Suri /hɔ/ ([1], Appendix E); not used in Amharic. 56 ህ ← h; 57 ለ ↔ lə; 58 ሉ ↔ lu; 59 ሊ ↔ li; 60 ላ ↔ la; 61 ሌ ↔ le; 62 ል ↔ lɨ; 63 ሎ ↔ lo; 64 ⶀ → lo; # Dizi, Me’en, Mursi, Suri /lɔ/ ([1], Appendix E); not used in Amharic. 65 ሏ ↔ lwa; 66 ል ← l; 67 # Appendix B of [1] transcribes ሐ as Voiceless pharyngeal fricative 68 # /ħə/. However, according to an Amharic-speaking person, Amharic 69 # makes no difference in pronunciation between ሐ...ሓ and ሀ...ሃ; both 70 # are pronounced as Voiceless glottal fricative /h/. Also, according 71 # to the speaker there is no /hə/ sequence in Amharic; instead, it 72 # gets pronounced as /ha/. 73 ሐ → ha; 74 ሑ → hu; 75 ሒ → hi; 76 ሓ → ha; 77 ሔ → he; 78 ሕ → hɨ; 79 ሖ → ho; 80 ሗ → hwa; 81 መ ↔ mə; 82 ሙ ↔ mu; 83 ሚ ↔ mi; 84 ማ ↔ ma; 85 ሜ ↔ me; 86 ም ↔ mɨ; 87 ሞ ↔ mo; 88 ⶁ → mo; # Dizi, Me’en, Mursi, Suri /mɔ/ ([1], Appendix E); not used in Amharic. 89 ᎀ → mwə; # Sebatbeit /mwə/ ([1], Appendix H); not used in Amharic. 90 ᎃ → mwu; # Sebatbeit /mwu/ ([1], Appendix H); not used in Amharic. 91 ᎁ → mwi; # Sebatbeit /mwi/ ([1], Appendix H); not used in Amharic. 92 ሟ ↔ mwa; 93 ᎂ → mwe; # Sebatbeit /mwe/ ([1], Appendix H); not used in Amharic. 94 ፙ → mja; # Unclear which language; Appendix L of [1] transcribes ፙ as /mʲa/. 95 ም ← m; 96 ሠ → sə; 97 ሡ → su; 98 ሢ → si; 99 ሣ → sa; 100 ሤ → se; 101 ሥ → sɨ; 102 ሦ → so; 103 ሧ → swa; 104 ረ ↔ rə; 105 ሩ ↔ ru; 106 ሪ ↔ ri; 107 ራ ↔ ra; 108 ሬ ↔ re; 109 ር ↔ rɨ; 110 ሮ ↔ ro; 111 ⶂ → ro; # Dizi, Me’en, Mursi, Suri /rɔ/ ([1], Appendix E); not used in Amharic. 112 ሯ ↔ rwa; 113 ፘ → rja; # Unclear which language; Appendix L of [1] transcribes ፘ as /rʲa/. 114 ር ← r; 115 # Amharic speakers pronounce ⶠ like ሸ. Source: [1], Appendix B. 116 ⶠ → ʃə; 117 ⶡ → ʃu; 118 ⶢ → ʃi; 119 ⶣ → ʃa; 120 ⶤ → ʃe; 121 ⶥ → ʃɨ; 122 ⶦ → ʃo; 123 ሸ ↔ ʃə; 124 ሹ ↔ ʃu; 125 ሺ ↔ ʃi; 126 ሻ ↔ ʃa; 127 ሼ ↔ ʃe; 128 ሽ ↔ ʃɨ; 129 ሾ ↔ ʃo; 130 ⶄ → ʃo; # Dizi, Me’en, Mursi, Suri /ʃɔ/ ([1], Appendix E); not used in Amharic. 131 ሿ ↔ ʃwa; 132 ሽ ← ʃ; 133 ቀ ↔ kʼə; 134 ቁ ↔ kʼu; 135 ቂ ↔ kʼi; 136 ቃ ↔ kʼa; 137 ቄ ↔ kʼe; 138 ቅ ↔ kʼɨ; 139 ቆ ↔ kʼo; 140 ቇ → kʼo; # Dizi, Me’en, Mursi, Suri /kʼɔ/ ([1], Appendix E); not used in Amharic. 141 ቈ ↔ kʼwə; 142 ቍ ↔ kʼwu; 143 ቊ ↔ kʼwi; 144 ቋ ↔ kʼwa; 145 ቌ ↔ kʼwe; 146 ቅ ← kʼ; 147 # In Awngi, Blin, Qimant, and Xamtanga, ቐ is spoken as voiced uvular fricative [ʁ]. 148 # Source: [1], Appendix C. However, */ʁ/ is not an Amharic phoneme. 149 # When reading foreign words with ቐ, Amharic speakers pronounce 150 # ቐ like ቀ, i.e. as velar ejective /kʼ/. 151 ቐ → kʼə; 152 ቑ → kʼu; 153 ቒ → kʼi; 154 ቓ → kʼa; 155 ቔ → kʼe; 156 ቕ → kʼɨ; 157 ቖ → kʼo; 158 ቘ → kʼwə; 159 ቝ → kʼwu; 160 ቚ → kʼwi; 161 ቛ → kʼwa; 162 ቜ → kʼwe; 163 # In Sebatbeit, ⷀ is spoken as palatalized velar ejective /kʼʲ/ ([1], Appendix H). 164 # In Amharic, the syllable is not used, but it might appear in names. 165 ⷀ → kʼjə; 166 ⷁ → kʼju; 167 ⷂ → kʼji; 168 ⷃ → kʼja; 169 ⷄ → kʼje; 170 ⷅ → kʼjɨ; 171 ⷆ → kʼjo; 172 በ ↔ bə; 173 ቡ ↔ bu; 174 ቢ ↔ bi; 175 ባ ↔ ba; 176 ቤ ↔ be; 177 ብ ↔ bɨ; 178 ቦ ↔ bo; 179 ⶅ → bo; # Dizi, Me’en, Mursi, Suri /bɔ/ ([1], Appendix E); not used in Amharic. 180 ᎄ → bwə; # Sebatbeit /bʷə/ ([1], Appendix H); not used in Amharic. 181 ᎇ → bwu; # Sebatbeit /bʷu/ ([1], Appendix H); not used in Amharic. 182 ᎅ → bwi; # Sebatbeit /bʷi/ ([1], Appendix H); not used in Amharic. 183 ቧ → bwa; # Sebatbeit /bʷa/ ([1], Appendix H); not used in Amharic. 184 ᎆ → bwe; # Sebatbeit /bʷe/ ([1], Appendix H); not used in Amharic. 185 ብ ← b; 186 ቨ ↔ və; 187 ቩ ↔ vu; 188 ቪ ↔ vi; 189 ቫ ↔ va; 190 ቬ ↔ ve; 191 ቭ ↔ vɨ; 192 ቮ ↔ vo; 193 ቯ ↔ vwa; 194 ቭ ← v; 195 # Unclear which Ethiopic language uses ⶨ. It only appears in the 196 # “Language Neutral” list of Appendix L in [1], which transcribes it as t\u0361ʃ. 197 # For Amharic, we pronounce ⶨ therefore like ቸ. 198 ⶨ → t\u0361ʃə; 199 ⶩ → t\u0361ʃu; 200 ⶪ → t\u0361ʃi; 201 ⶫ → t\u0361ʃa; 202 ⶬ → t\u0361ʃe; 203 ⶭ → t\u0361ʃɨ; 204 ⶮ → t\u0361ʃo; 205 # In Amharic, ኀ is pronounced like ሀ. 206 # Source: [1], section on “Phonological Redundancy” for Amharic, page 5. 207 # Appendix B of [1] transcribes ሀ as /hə/. However, according to 208 # an Amharic-speaking person, there is no /hə/ sequence in Amharic. 209 # Instead, ሀ (and hence also ኀ) gets pronounced as /ha/. 210 ኀ → ha; 211 ኁ → hu; 212 ኂ → hi; 213 ኃ → ha; 214 ኄ → he; 215 ኅ → hɨ; 216 ኆ → ho; 217 ኇ → ho; # Dizi, Me’en, Mursi, Suri /ŋɔ/ ([1], Appendix E); not used in Amharic. 218 ኈ → hwə; 219 ኍ → hwu; 220 ኊ → hwi; 221 ኋ → hwa; 222 ኌ → hwe; 223 ነ ↔ nə; 224 ኑ ↔ nu; 225 ኒ ↔ ni; 226 ና ↔ na; 227 ኔ ↔ ne; 228 ን ↔ nɨ; 229 ኖ ↔ no; 230 ⶈ → no; # Dizi, Me’en, Mursi, Suri /nɔ/ ([1], Appendix E); not used in Amharic. 231 ኗ ↔ nwa; 232 ን ← n; 233 ኘ ↔ ɲə; 234 ኙ ↔ ɲu; 235 ኚ ↔ ɲi; 236 ኛ ↔ ɲa; 237 ኜ ↔ ɲe; 238 ኝ ↔ ɲɨ; 239 ኞ ↔ ɲo; 240 ⶉ → ɲo; # Dizi, Me’en, Mursi, Suri /ɲɔ/ ([1], Appendix E); not used in Amharic. 241 ኟ ↔ ɲwa; 242 ኝ ← ɲ; 243 # Amharic speakers pronounce ኸ as [h] because Amharic has no [x] sound. 244 # However, in transliterations of foreign (eg. Spanish) words with [x], 245 # several Amharic speakers have confirmed that they prefer ኻ over ሃ. 246 ዀ → hwə; 247 ዂ → hwi; 248 ዃ → hwa; 249 ዄ → hwe; 250 ዅ → hwɨ; 251 ኸ → hə; 252 ኹ → hu; 253 ኺ → hi; 254 ኻ → ha; 255 ኼ → he; 256 ኽ → hɨ; 257 ኾ → ho; 258 ዀ ← xwə; 259 ዂ ← xwi; 260 ዃ ← xwa; 261 ዄ ← xwe; 262 ዅ ← xwɨ; 263 ዅ ← xw; 264 ኸ ← xə; 265 ኹ ← xu; 266 ኺ ← xi; 267 ኻ ← xa; 268 ኼ ← xe; 269 ኽ ← xɨ; 270 ኾ ← xo; 271 ኽ ← x; 272 አ ↔ ʔə; 273 ኡ ↔ ʔu; 274 ኢ ↔ ʔi; 275 ኣ ↔ ʔa; 276 ኤ ↔ ʔe; 277 እ ↔ ʔɨ; 278 ኦ ↔ ʔo; 279 ⶊ → ʔo; # Dizi, Me’en, Mursi, Suri /ɲɔ/ ([1], Appendix E); not used in Amharic. 280 እ ← ʔ; 281 ከ ↔ kə; 282 ኩ ↔ ku; 283 ኪ ↔ ki; 284 ካ ↔ ka; 285 ኬ ↔ ke; 286 ክ ↔ kɨ; 287 ኮ ↔ ko; 288 ኰ ↔ kwə; 289 ኵ ↔ kwu; 290 ኲ ↔ kwi; 291 ኳ ↔ kwa; 292 ኴ ↔ kwe; 293 ክ ← k; 294 # In Sebatbeit, ⷈ is spoken as palatalized velar plosive /kʲ/ ([1], Appendix H). 295 # Amharic speakers pronounce it as /k/ without palatalization. 296 ⷈ → kə; 297 ⷉ → ku; 298 ⷊ → ki; 299 ⷋ → ka; 300 ⷌ → ke; 301 ⷍ → kɨ; 302 ⷎ → ko; 303 # In Sebatbeit, ⷐ is spoken as palatalized voiceless velar fricative/xʲə/ 304 # according to [1], Appendix H. When the syllable appears in names, 305 # Amharic speakers pronounce it as /kə/ without palatalization. 306 ⷐ → kə; 307 ⷑ → ku; 308 ⷒ → ki; 309 ⷓ → ka; 310 ⷔ → ke; 311 ⷕ → kɨ; 312 ⷖ → ko; 313 ወ ↔ wə; 314 ዉ ↔ wu; 315 ዊ ↔ wi; 316 ዋ ↔ wa; 317 ዌ ↔ we; 318 ው ↔ wɨ; 319 ዎ ↔ wo; 320 ዏ → wo; # Dizi, Me’en, Mursi, Suri /wɔ/ ([1], Appendix E); not used in Amharic. 321 ው ← w; 322 ዐ ↔ ʕə; 323 ዑ ↔ ʕu; 324 ዒ ↔ ʕi; 325 ዓ ↔ ʕa; 326 ዔ ↔ ʕe; 327 ዕ ↔ ʕɨ; 328 ዖ ↔ ʕo; 329 ዒ ← ʕ; 330 ዘ ↔ zə; 331 ዙ ↔ zu; 332 ዚ ↔ zi; 333 ዛ ↔ za; 334 ዜ ↔ ze; 335 ዝ ↔ zɨ; 336 ዞ ↔ zo; 337 ⶋ → zo; # Dizi, Me’en, Mursi, Suri /zɔ/ ([1], Appendix E); not used in Amharic. 338 ዟ ↔ zwa; 339 ዝ ← z; 340 ዠ ↔ ʒə; 341 ዡ ↔ ʒu; 342 ዢ ↔ ʒi; 343 ዣ ↔ ʒa; 344 ዤ ↔ ʒe; 345 ዥ ↔ ʒɨ; 346 ዦ ↔ ʒo; 347 ዧ ↔ ʒwa; 348 ዢ ← ʒ; 349 # Unclear which Ethiopic language uses ⶰ. It only appears in the 350 # “Language Neutral” list of Appendix L in [1], which transcribes it as ʒ. 351 # For Amharic, we pronounce ⶰ therefore like ዠ. 352 ⶰ → ʒə; 353 ⶱ → ʒu; 354 ⶲ → ʒi; 355 ⶳ → ʒa; 356 ⶴ → ʒe; 357 ⶵ → ʒɨ; 358 ⶶ → ʒo; 359 የ ↔ jə; 360 ዩ ↔ ju; 361 ዪ ↔ ji; 362 ያ ↔ ja; 363 ዬ ↔ je; 364 ይ ↔ jɨ; 365 ዮ ↔ jo; 366 ዯ → jo; # Dizi, Me’en, Mursi, Suri /zɔ/ ([1], Appendix E); not used in Amharic. 367 ይ ← j; 368 ጀ ↔ d\u0361ʒə; 369 ጁ ↔ d\u0361ʒu; 370 ጂ ↔ d\u0361ʒi; 371 ጃ ↔ d\u0361ʒa; 372 ጄ ↔ d\u0361ʒe; 373 ጅ ↔ d\u0361ʒɨ; 374 ጆ ↔ d\u0361ʒo; 375 ጇ ↔ d\u0361ʒwa; 376 ጅ ← d\u0361ʒ; 377 ደ ↔ də; 378 ዱ ↔ du; 379 ዲ ↔ di; 380 ዳ ↔ da; 381 ዴ ↔ de; 382 ድ ↔ dɨ; 383 ዶ ↔ do; 384 ⶌ → do; # Dizi, Me’en, Mursi, Suri /zɔ/ ([1], Appendix E); not used in Amharic. 385 ዷ ↔ dwa; 386 ድ ← d; 387 ገ ↔ ɡə; 388 ጉ ↔ ɡu; 389 ጊ ↔ ɡi; 390 ጋ ↔ ɡa; 391 ጌ ↔ ɡe; 392 ግ ↔ ɡɨ; 393 ጎ ↔ ɡo; 394 ጐ ↔ ɡwə; 395 ጕ ↔ ɡwu; 396 ጒ ↔ ɡwi; 397 ጓ ↔ ɡwa; 398 ጔ ↔ ɡwe; 399 ግ ← ɡ; 400 # In Awngi, Blin, Qimant, and Xamtanga, ጘ is spoken as voiced velar nasal [ŋ]. 401 # Source: [1], Appendix C. While /ŋ/ is not an Amharic phoneme, Amharic speakers 402 # still can pronounce it according to our source. However, when transliterating 403 # foreign words with [ŋ], Amharic uses the sequence ንግ /nɡ/. For example, 404 # the Amharic transliteration of Washington /waʃiŋtən/ is ዋሺንግተን. 405 ጘ → ŋə; 406 ጙ → ŋu; 407 ጚ → ŋi; 408 ጛ → ŋa; 409 ጜ → ŋe; 410 ጝ → ŋɨ; 411 ጞ → ŋo; 412 ⶓ → ŋwə; 413 ⶖ → ŋwu; 414 ⶔ → ŋwi; 415 ጟ → ŋwa; 416 ⶕ → ŋwe; 417 # Since there is no uvular nasal [ɴ] in Amharic, we use the velar nasal [ŋ]. 418 ጘ ← ɴə; 419 ጙ ← ɴu; 420 ጚ ← ɴi; 421 ጛ ← ɴa; 422 ጜ ← ɴe; 423 ጝ ← ɴɨ; 424 ጞ ← ɴo; 425 ጝ ← ɴ; 426 # In Sebatbeit, ⷘ is spoken as palatalized voiced velar stop /ɡj/ ([1], Appendix H). 427 # Amharic speakers pronounce it as voiced velar stop /ɡ/ without palatalization. 428 ⷘ → ɡə; 429 ⷙ → ɡu; 430 ⷚ → ɡi; 431 ⷛ → ɡa; 432 ⷜ → ɡe; 433 ⷝ → ɡɨ; 434 ⷞ → ɡo; 435 ጠ ↔ tʼə; 436 ጡ ↔ tʼu; 437 ጢ ↔ tʼi; 438 ጣ ↔ tʼa; 439 ጤ ↔ tʼe; 440 ጥ ↔ tʼɨ; 441 ጦ ↔ tʼo; 442 ጧ ↔ tʼwa; 443 ጢ ← tʼ; 444 ጨ ↔ t\u0361ʃʼə; 445 ጩ ↔ t\u0361ʃʼu; 446 ጪ ↔ t\u0361ʃʼi; 447 ጫ ↔ t\u0361ʃʼa; 448 ጬ ↔ t\u0361ʃʼe; 449 ጭ ↔ t\u0361ʃʼɨ; 450 ጮ ↔ t\u0361ʃʼo; 451 ⶐ → t\u0361ʃʼo; # Dizi, Me’en, Mursi, Suri /t\u0361ʃʼɔ/ ([1], Appendix E); not used in Amharic. 452 ጯ ↔ t\u0361ʃʼwa; 453 ጪ ← t\u0361ʃʼ; 454 # According to Appendix B of [1], the following are used in the Bench language 455 # (aka Benchnon, Gimira). In Bench, ⶻ is pronounced as /ʈ\u0361ʂʼ/ Retroflex 456 # ejective affricate; with a phonemic distrinction to the non-retroflex version. 457 # Amharic does not have retroflex phonemes, so we go with /t\u0361ʃʼ/. 458 ⶸ → t\u0361ʃʼə; 459 ⶹ → t\u0361ʃʼu; 460 ⶺ → t\u0361ʃʼi; 461 ⶻ → t\u0361ʃʼa; 462 ⶼ → t\u0361ʃʼe; 463 ⶽ → t\u0361ʃʼɨ; 464 ⶾ → t\u0361ʃʼo; 465 ቸ ↔ t\u0361ʃə; 466 ቹ ↔ t\u0361ʃu; 467 ቺ ↔ t\u0361ʃi; 468 ቻ ↔ t\u0361ʃa; 469 ቼ ↔ t\u0361ʃe; 470 ች ↔ t\u0361ʃɨ; 471 ቾ ↔ t\u0361ʃo; 472 ቿ ↔ t\u0361ʃwa; 473 ች ← t\u0361ʃ; 474 ተ ↔ tə; 475 ቱ ↔ tu; 476 ቲ ↔ ti; 477 ታ ↔ ta; 478 ቴ ↔ te; 479 ት ↔ tɨ; 480 ቶ ↔ to; 481 ⶆ → to; # Dizi, Me’en, Mursi, Suri /tɔ/ ([1], Appendix E); not used in Amharic. 482 ቷ ↔ twa; 483 ት ← t; 484 ጰ ↔ pʼə; 485 ጱ ↔ pʼu; 486 ጲ ↔ pʼi; 487 ጳ ↔ pʼa; 488 ጴ ↔ pʼe; 489 ጵ ↔ pʼɨ; 490 ጶ ↔ pʼo; 491 ⶑ → pʼo; # Dizi, Me’en, Mursi, Suri /pʼɔ/ ([1], Appendix E); not used in Amharic. 492 ጷ ↔ pʼwa; 493 ጵ ← pʼ; 494 ጸ ↔ sʼə; 495 ጹ ↔ sʼu; 496 ጺ ↔ sʼi; 497 ጻ ↔ sʼa; 498 ጼ ↔ sʼe; 499 ጽ ↔ sʼɨ; 500 ጾ ↔ sʼo; 501 ጿ ↔ sʼwa; 502 ጽ ← sʼ; 503 # In Amharic, ፀ is pronounced like ጸ. 504 # Source: [1], section on “Phonological Redundancy” for Amharic, page 5. 505 ፀ → sʼə; 506 ፁ → sʼu; 507 ፂ → sʼi; 508 ፃ → sʼa; 509 ፄ → sʼe; 510 ፅ → sʼɨ; 511 ፆ → sʼo; 512 ፇ → sʼo; # Dizi, Me’en, Mursi, Suri /sʼɔ/ ([1], Appendix E); not used in Amharic. 513 # Amharic speakers pronounce ሰ like ሠ. Source: [1], Appendix B. 514 ሰ ↔ sə; 515 ሱ ↔ su; 516 ሲ ↔ si; 517 ሳ ↔ sa; 518 ሴ ↔ se; 519 ስ ↔ sɨ; 520 ሶ ↔ so; 521 ⶃ → so; # Dizi, Me’en, Mursi, Suri /sɔ/ ([1], Appendix E); not used in Amharic. 522 ሷ ↔ swa; 523 ስ ← s; 524 ፈ ↔ fə; 525 ፉ ↔ fu; 526 ፊ ↔ fi; 527 ፋ ↔ fa; 528 ፌ ↔ fe; 529 ፍ ↔ fɨ; 530 ፎ ↔ fo; 531 ᎈ → fwə; # Sebatbeit /fwə/ ([1], Appendix H); not used in Amharic. 532 ᎉ → fwu; # Sebatbeit /fwu/ ([1], Appendix H); not used in Amharic. 533 ᎋ → fwi; # Sebatbeit /fwi/ ([1], Appendix H); not used in Amharic. 534 ፏ ↔ fwa; 535 ᎊ → fwe; # Sebatbeit /fwe/ ([1], Appendix H); not used in Amharic. 536 ፚ → fja; # Unclear which language; Appendix L of [1] transcribes ፚ as /fja/. 537 ፍ ← f; 538 ፐ ↔ pə; 539 ፑ ↔ pu; 540 ፒ ↔ pi; 541 ፓ ↔ pa; 542 ፔ ↔ pe; 543 ፕ ↔ pɨ; 544 ፖ ↔ po; 545 ⶒ → po; # Dizi, Me’en, Mursi, Suri /pɔ/ ([1], Appendix E); not used in Amharic. 546 ᎌ → pwə; # Sebatbeit /pwə/ ([1], Appendix H); not used in Amharic. 547 ᎍ → pwu; # Sebatbeit /pwu/ ([1], Appendix H); not used in Amharic. 548 ᎏ → pwi; # Sebatbeit /pwi/ ([1], Appendix H); not used in Amharic. 549 ፗ ↔ pwa; 550 ᎎ → pwe; # Sebatbeit /pwe/ ([1], Appendix H); not used in Amharic. 551 ፕ ← p; 552 ኧ ↔ ə; 553 ኡ ← u; # ኡላዓን ባዓታር ← Ulaan Baatar /ulaʕan baʕatar/ 554 አ ← a; # አምስተርዳም ← Amsterdam /amstərdam/ 555 ኤ ← e; 556 እ ← ɨ; 557 ኦ ← o; # ፖርት ኦፍ ስፔን ← Port of Spain /port of speːn/ 558 ኢ ← i; # ኢስላማባድ ← Islamabad /islamabad/ 559 # Applications will typically split words before calling our rules. 560 # To be resilient, we replace punctuation by whitespace in IPA. 561 ፠ → ' '; # U+1360 ETHIOPIC SECTION MARK 562 ፡ → ' '; # U+1361 ETHIOPIC WORDSPACE 563 ። → ' '; # U+1362 ETHIOPIC FULL STOP 564 ፣ → ' '; # U+1363 ETHIOPIC COMMA 565 ፤ → ' '; # U+1364 ETHIOPIC SEMICOLON 566 ፥ → ' '; # U+1365 ETHIOPIC COLON 567 ፦ → ' '; # U+1366 ETHIOPIC PREFACE COLON 568 ፧ → ' '; # U+1367 ETHIOPIC QUESTION MARK 569 ፨ → ' '; # U+1368 ETHIOPIC PARAGRAPH SEPARATOR 570 # Likewise, Ethiopic numerals cannot be pronounced by these rules, 571 # so we replace them by whitespace in the output IPA notation. 572 # Applications will typically pre-process text before calling 573 # the am → am_FONIPA transform. 574 ፩ → ' '; # U+1369 ETHIOPIC DIGIT ONE 575 ፪ → ' '; # U+136A ETHIOPIC DIGIT TWO 576 ፫ → ' '; # U+136B ETHIOPIC DIGIT THREE 577 ፬ → ' '; # U+136C ETHIOPIC DIGIT FOUR 578 ፭ → ' '; # U+136D ETHIOPIC DIGIT FIVE 579 ፮ → ' '; # U+136E ETHIOPIC DIGIT SIX 580 ፯ → ' '; # U+136F ETHIOPIC DIGIT SEVEN 581 ፰ → ' '; # U+1370 ETHIOPIC DIGIT EIGHT 582 ፱ → ' '; # U+1371 ETHIOPIC DIGIT NINE 583 ፲ → ' '; # U+1372 ETHIOPIC NUMBER TEN 584 ፳ → ' '; # U+1373 ETHIOPIC NUMBER TWENTY 585 ፴ → ' '; # U+1374 ETHIOPIC NUMBER THIRTY 586 ፵ → ' '; # U+1375 ETHIOPIC NUMBER FORTY 587 ፶ → ' '; # U+1376 ETHIOPIC NUMBER FIFTY 588 ፷ → ' '; # U+1377 ETHIOPIC NUMBER SIXTY 589 ፸ → ' '; # U+1378 ETHIOPIC NUMBER SEVENTY 590 ፹ → ' '; # U+1379 ETHIOPIC NUMBER EIGHTY 591 ፺ → ' '; # U+137A ETHIOPIC NUMBER NINETY 592 ፻ → ' '; # U+137B ETHIOPIC NUMBER HUNDRED 593 ፼ → ' '; # U+137C ETHIOPIC NUMBER TEN THOUSAND 594 # Transform IPA length markers to one of these: 595 # U+135D ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK 596 # U+135E ETHIOPIC COMBINING VOWEL LENGTH MARK 597 # U+135F ETHIOPIC COMBINING GEMINATION MARK 598 ::null(); 599 ← ː ; # Strip off any remaining IPA length markers. 600 ::(null); 601 ($IPA_CONSONANT) ([jw]? $IPA_VOWEL) \u135D → $1 ː $2 ː; 602 ($IPA_CONSONANT) ([jw]? $IPA_VOWEL) \u135E → $1 $2 ː; 603 ($IPA_CONSONANT) ([jw]? $IPA_VOWEL?) \u135F → $1 ː $2; 604 [\u135D \u135E \u135F] → ; # Strip off any remaining length markers. 605 $1 wa \u135D ← ($LABIALIZABLE_BEFORE_A) ː waː; # ቷ\u135D ← [tːʷaː] 606 $1 wa \u135E ← ($LABIALIZABLE_BEFORE_A) waː; # ቷ\u135E ← [tʷaː] 607 $1 wa \u135F ← ($LABIALIZABLE_BEFORE_A) ː wa; # አቷ\u135F ← [tːʷa] 608 $1 \u135F $2 \u135E ← ([b $LABIALIZABLE_BEFORE_A]) ː ([jw] $IPA_VOWEL) ː; 609 $1 \u135F $2 ← {([b $LABIALIZABLE_BEFORE_A]) ː ([jw] $IPA_VOWEL?)}; 610 $1 \u135E ← ($IPA_VOWEL ː); 611 $1 \u135D ← (jː $IPA_VOWEL ː); 612 $1 \u135E ← ([jw] $IPA_VOWEL ː); 613 $1 \u135F ← (jː $IPA_VOWEL?); 614 $1 \u135D ← ($IPA_CONSONANT ː [w]? $IPA_VOWEL ː); 615 $1 \u135E ← ($IPA_CONSONANT [w]? $IPA_VOWEL ː); 616 $1 \u135F ← ($IPA_CONSONANT ː [w]? $IPA_VOWEL?); 617 # Insert syllable markers in a separate pass. 618 ::null; 619 {($IPA_VOWEL ː?)} [[:L:]] → $1 \.; 620 ::(null); 621 ← [ˈˌ\. \u0303\u032F]; 622 aj ← ai; # Nairobi /nairobi/ ናይሮቢ, Cairo /kairo/ ካይሮ 623 aw ← au; # Bissau /bisːau/ ቢሳው 624 eji ← ei; # Beijing /beid\u0361ʒiŋ/ ቤዪጂንግ 625 ewo ← eo; # Montevideo /montevideo/ ሞንቴቪዴዎ 626 ija ← ia; # Monrovia /monrovia/ ሞንሮቪያ 627 ijə ← iə; # Reunion /rijunijən/ ሪዩኒየን 628 iw ← iu; # Vilnius /vilnius/ ቪልኒውስ, New Delhi /niu deːli/ ኒው ዴሊ 629 jo ← io; # Tokyo /tokio/ ቶክዮ 630 nɡ ← ŋɡ; # Kongo /koŋɡo/ ኮንጎ, Hungary /həŋɡari/ ሀንጋሪ 631 nɡ ← ŋ; # Bangkok /baŋkok/ ባንግኮክ, Beijing /beid\u0361ʒiŋ/ ቤዪጂንግ 632 uwa ← ua; # Kuala Lumpur /kuala lumpur/ ኩዋላ ሉምፑር, Ruanda /ruanda/ ሩዋንዳ 633 bwe ← bue; # Buenos Aires /buenos aires/ ብዌኖስ አይሬስ 634 sʼ ← t\u0361s; # Podgorica /podɡorit\u0361sa/ ፖድጎሪጻ, Vaduz /fadut\u0361s/ ፋዱጽ 635 uwi ← ui; # Port Luis /port luis/ ፖርት ሉዊስ 636 uwe ← ue; # Lithuania /lituenia/ ሊቱዌኒያ, Venezuela /venɨzuela/ ቬንዙዌላ 637 ::(null); 638 ʔə ← \. ə; 639 ʔu ← \. u; 640 ʔi ← \. i; 641 ʔa ← \. a; 642 ʔe ← \. e; 643 ʔɨ ← \. ɨ; 644 ʔo ← \. o; 645 $1 w ← {($IPA_VOWEL ː?) \u032F} $IPA_VOWEL; # /ewowa/ ← /e\u032Fo\u032Fa/ 646 ::(null); 647 n ← [n {n\u033C} {n\u033C\u030A} {m\u033A} {n\u030A} {n\u0325} ⁿ ᵑ]; 648 m ← [ɱ {m\u0325} {m\u032A} ᵐ]; 649 ɲ ← [{ɳ\u030A} {ɳ\u0325} ɳ {ɲ\u030A} {ɲ\u0325} ɲ]; 650 ŋ ← [{ŋ\u030A} {ŋ\u0325} ŋ]; 651 ɴ ← [{ɴ\u030A} {ɴ\u0325} ɴ]; 652 p ← [{t\u033C} {p\u033A}]; 653 pʼ ← [ʘ ɋ]; 654 b ← [{d\u033C} {b\u033A} {ɾ\u033C} ɓ]; 655 t ← [{t\u032A} ʈ]; 656 tʼ ← [ǁ ʖ]; 657 d ← [ɖ ɗ ᶑ]; 658 k ← q; 659 kʼ ← [ǃ ʗ]; 660 ɡ ← [g ɢ ɣ ɠ ʛ]; 661 nɡ ← ᵑɡ; 662 ʔ ← ʡ; 663 s ← [θ {θ\u0331} {θ\u031E} {θ\u033C} {ɸ\u033A}]; 664 z ← [ð {ð\u0320} {ð\u033C} {β\u033A}]; 665 sʼ ← [{t\u0361s} {t\u035Cs} ʦ]; 666 t\u0361ʃ ← [{t\u035Cʃ} ʧ {t\u0361ɕ} {t\u035Cɕ} ʨ {ʈ\u0361ʂ} c]; 667 t\u0361ʃʼ ← [ǀ ʇ ǂ ʄ]; 668 d\u0361ʒ ← [ʤ ʣ {d\u0361z} {d\u035Cz} {d\u0361ɕ} ʥ {d\u0361ʑ} {d\u035Cʑ} {ɖ\u0361ʐ} {d\u0361ʐ} ɟ]; 669 pf ← [{p\u032A} {p\u0346} ȹ {p\u0361f} {p\u032Af} {p\u032A\u035Cf}]; 670 bv ← [{b\u032A} {b\u0346} ȸ {b\u0361v} {b\u032A\u0361v}]; 671 ʃ ← [ʂ ɕ]; 672 ʒ ← [ʐ ʑ]; 673 r ← [ɾ ɽ ʁ]; 674 rːʒ ← r\u031Dː; 675 rʒ ← r\u031D; 676 v ← β; 677 x ← [ç x χ]; 678 ʕ ← ʕ\u031D; 679 h ← ɦ; 680 j ← [ʝ ʲ]; 681 lj ← ʎ [iɨ]? [jʝʲ]?; 682 t\u0361ʃl ← [{t\u0361ɬ} {tɬ}]; 683 ʃl ← ɬ; 684 w ← {u\u032F} $IPA_VOWEL; 685 w ← ʷ; 686 ʼː ← ːʼ; # /pʼː/ ← /pːʼ/; /sʼː/ ← /sːʼ/; etc. 687 ::(null); 688 i ← y; 689 ɨ ← [ɪ ʉ]; 690 u ← [ʊ ɯ]; 691 ə ← [ɛ æ ɘ]; 692 o ← [ɔ ø]; 693 a ← ɑ; 694 ʼ ← ʰ; 695 ← [ʱ]; 696 $1ːʲ ← ([pbtd])ʲː; # [bːʲeː] ← [bʲːeː] 697 $1ːʷ ← ([pbtd])ʷː; # [bːʷeː] ← [bʷːeː] 698 ::(NFC); 699 ← [ \u0303 \u0330 \u030B \u0301 \u0304 \u0300 \u030F \u030C \u0302 ˥ ˦ ˧ ˨ ˩ ꜜ ꜛ ↗ ↘ ]; 700 ::(NFD);