From 7ce445e528f1cd9644e8c7d4fd2d1a40ecc144d6 Mon Sep 17 00:00:00 2001 From: roedoejet Date: Fri, 14 May 2021 10:38:49 -0700 Subject: [PATCH] refactor(moh): replace H and L with 1 and 2for festival format, change stress to high tone --- g2p/mappings/langs/langs.pkl | Bin 259311 -> 259095 bytes g2p/mappings/langs/moh/abbreviations.csv | 2 +- g2p/mappings/langs/moh/moh_to_festival.csv | 36 ++++++------ g2p/mappings/langs/moh/moh_to_ipa.json | 12 ++-- g2p/tests/public/data/moh.psv | 62 ++++++++++----------- 5 files changed, 56 insertions(+), 56 deletions(-) diff --git a/g2p/mappings/langs/langs.pkl b/g2p/mappings/langs/langs.pkl index fa423795921a90874b1864363bbf5e6f787b654d..98ea035f5a835719cfbf3e0af75b5e7a29e5cedd 100644 GIT binary patch delta 19579 zcmeHPdvKIhmZ!hl;UPg_$b**>6%nIM67aq2%1eO|-oAHbiIBC^U|OrwL)00Q@U)ml zf@ZirW;B$}j0mWZVI!#HXeTSl#8szu)f#842|Keou88PP)vmiW?m546zwhhY-`8=g z_TRNE`s;Ik=W)+H_uSXlIrYcU`s2|pTOwPWc6ILXlV1+OfBG*bsHI1m)U?YA;`g6B zWQczHGPPr9U%G#Df2)4-ay3ogdbxVFAU^**;!U|iH5bHhCRo?gSEvgj(Vl&Ts=Z7V z>3_LWZ7Yc1K&Y<7RjNLspIV_N>(leqEFD>?#_K67)wMdlQk|`LtyC3V|M{0{Qe@)u zbB7E`M;nu|`u6xCelBQyb8p|~_IRg0bg3#T0bj+EF5B^WqlDL(yoW_~+ghh|G?QXU zXo}4@I=%&BO4K{OdtKe7kayN^G?t^id;7XvW}zt0?7fP(ddxMdyuwgAm;$de9lvaA zkDV8r8aqEWHTAvr>2c9m3&g{%9~3t;0YQZbo&o}~<>K%104E*IJk#Ks8;%}n2{lKQDye|kbSJZpMvv1pwY-P2^VKvfFD~Z;aVu1aaQQ-CG?RGif=UCbTQ1;{Fu)kDP=cUDA%t#PpsL0j$}>!12Tjds z(622}6OGRa&MU*^ybCdk>R}-J!XdT&Ev^=NB#jNQ_t&ehx(ympLfM`87Ze%Tt2LDc z$dQbke&e#6uC2K+N8rCHRN|lv)V!Kwm-s-=*#`a6LN#e5g5YrVxLpq{R3$eGq0VhK zidV4J4wrf~TJcN~0!a7(8cTZ23bk|4T)DhUEmj92BW0>MC+*Z$>6dEMWmBqZEcLM| z)KQp!&Pl7@8NXURn<{^z8lbxVU{Zt;(iAn|o_iCR4pMVBZ}U6uar5;ci6 zeZ`+uHG0Y#b>2u!`3$J9($_6jmoel1r2?$|jT)z)TdJO9;<9Dx>?t#Y&Pw$mn+dX+ zUZ$?T7A1jICaQu>LlI$gh^h>iB6dGfRns+kxq2}FQsbwz)NuYkm~OoOZ^7(J+^XIx zZLU~ARp;(_C4VHWln19pI4uEA+G(H~!(wUGkUK{}v|2>%>5e(HD(uE~@uHkhI?;6+)M4+~840gEEwSJJCWl zS(LfN-UDI8{aHlU;SE_d*GSJM)>oBMlU+*hfdFN{OBo4AoW>0u~X#6Dk%|N@g3j8Bm%<}w`EDwGNx4-ACs({ zx^(!!5&h=gWZw(c;ExMx-M!qBC%&U5h^pw?80;<3yWVpqiw|mTj13A&qF%5zCKiQg z!m^g8^-4W^qnbQ|wa3a>=!5sXm?W9MK)2o&abt3?P|DtSisp(#N#l0RUQs|_6B-o4 ziT`6M2X0T3Dt3EOqIOP`n&9>sg2n_lvLAa zQ+$yG?GA*I`r7FY?d3Z>t837*xzaLw-OQYLeHk*)JOxTiY^z9a4RF#A=_o-47>skBD44D-I2+RvswZ>I!%zhDu=~{* z<3uW(k;jSs-;Bu|&BlZ|5!)`YakofCa=3xuL^FFcbb>bqMdV(eJ&Zhg8%jWZ4F-Y;?cVT;$Wo}GxBer~Hz+Al%+#7B`zG-7P4 zhaz2AApBL9;7)j~|CUh3m!AD_kDE$C(vfYRFPRQ_sSmdLaXA3@+_+G zr4ds$d2z{fpr_#r#pSh4zAp!)!#8a59M2p^hYPsf0v|=c>$YuPET}CA&j1;7^YMVy z$AM!slL?0_kL;Dlce6HK+jG|w0$p815|(pE>K4-fsogpFjk~m65 zaZAWN;z-}0en5?z$>%jJCI`rf10TKS9O40i<4Y>aul>O(fhjp}6B(|*K~wRyeB@cF zPm*`=KmO)a5Jo@X5^$`8ILTYkGrj98aOS&vG<_hR13%6VlpQ^j4mEz zI~majcc{`a+0+-><3g*Y{ynu&)1+?C!Ta%!R2FLoj9eHu?l}sd}KmWce83{LV5fjm4 z)2i4dJVc6g6%nQ}BGx3Kwl_@7k!=w*Khi|IP-s()a92NFk{bWVecc zL5}P}sJ*-gkxrC72sGJy5VS{j8Q|Kx3~(JjMg?Vq&hwKosK-7=VHIzLkl zbPXa(+^xPWo$PzpWu~!R+kAEicYA)WQyUj1oq_f~84o_ryP{iruzSD2D`FZ^;d?tdl*y*KBGI??6 zNTkRe%{z$FRk2&Gjm&t8%Y&N7sr6%2yzXswtOc+L0R8Giq*f^XM;4Qa{@p{Wq**8f zFVc{L616yYR&o(P^AU%_>@4o5+27R>is(O5V-U{qS42g#dq-=m9Hm{p=vdkxs$;2d zB@beiACR8M!W_MxG#euWx};r=F=4qLs`Z$5FD(5>u6G^o`AL|nn|yC>3itPBA8~Ui z!g>8gV|%31t*0kvUA*vxn+Ae~{J*oZ>S?;#!hGs@K7haaY0-8cTLv2J<0a0l|Y{`4DZ3#D2~| z6kav+^lYsrG=rc%`4JUnY0%w$T{Qg!8>CKbqMhx z1$<-~&|J}~fj;S>?dt+TuaK5d66A@QLxYR@lvf%{q3=(gK6`Beea`Wp8--X>_25wnf3GPV+3Pp zWp;8=*Bg(i)=1&sRTC2z*|BQP$Ck}ZNjqFjV)R6_W%dg$hDq~De&#cSF=>S4m!vz7 zSOJWp`gD!_k-9Ka_#iu^8XM^_xlPZ0g63JFtXr2$$--POm}HC&0^3+Ylvc!t?O*~z z?;i0&Q80M68Y~#OeQ494J)y=|88KWbL9Cz=`-Y&L)3A;;>nAojB}*XYG_cQTP(%NZ zL)>xDC<4U4pd;@Pl?X#M=jme6*hrfJXmsc)M1ZeS2IX%czTVrRN=8AUEXB!dE~+zx zgtfG|&5t2g?!29~tnQ$#qqxPFE^WGn)EWX`PKg~+>fGanBHq6vOef#VkRQ005v6y~ z1tL+n5E-p}pVg)-AE9c;5ZPG~gsWXMQ|P9W9naY%g3}@#yX1khT{!k=1t%pOdsz<7 z+yJMU_V3J+Z3BCOr$F@R_5v>2GZd8OcdakWp{f1{=zs1{9-Y09&}gu_pao7nL-cH)PzS^sB1r00kOoRUdlioWEd+-S2_6qNfKEstX1@;zvFXCGXB}|L zU4`vX*!AyEt7{9-KevX=x5TI7!-_6*=t7?A(^S3skSbjdXthA?NgbT+!m&pLl$gtP zwvirM#pfa`?KX)i9{#`#tJ1UIb&5s`nQy44>aP#c(ozUKpr_Wz1vOJ-L=y!g8W>Zu zp{;-{Cc_O7xC#5E8x;ehe{_@)7(Pf~f6(#*bOf`Kef`^AUCQMl|cV)jQmB zJ@b^*8%Pc!;VVgmBT|CUEnlkQTcNgqeDeZHUp9w^lHLl>LXn5zsCt8<&Au9M^pjJ* zesU{Zk{t6K*oq(93uFE%vV!X+sZh@hVQlI58vNn=~oDBYt>#64`phGV{7VdqvHOG=F;u zR+W|bunH%0($N#GudbszRDR|aW&jbR_dHqFUS>ioy?MeMdzlFiy|l+1n)TOao#4Zu ze{&}`t8!Ly*&sT79t7mx>(QH>zfi>&LJ${uux;)qcdJV;LR2rHG<=*LurkQ;Y1-pr^t>~8s0O&2ZMaC9NI0#Ba zEKtQQS#&ZEYpOtZ)7ed*X=^xuR;7^UMOTP4mZAXg!YdmvDlRVdJ_VQV+Np}lK~eNu z8gV_ID+3Ywg$^}=@fR~53sLbQ6pr^7S)z?3rm+OSaEOm=cZ@f9;cy97ni4WqOGBFO zxd&dSjiLBg2MTFOt4ruHs72Mgh@9=C$R}KGT3s40pK=lQ8RckklBz3LG|MTPhlMtX zTQntmm@vl*WF|sz^0`Knv#$fI)lzRsgw~OBJZa=QC$zzx^Dudw^Z0`}=V2srLFafT zA?MyXu1d}nhiL^Pv_E&N(kh`*)d!6ocIq2K`j~=c#D4J)s&tl!(PG6HONEJf^O5mk z3|-Gk#IkTxzi4bvL{9q3%dV}FA^}sBg+><&GE$xZl0LH7bD8P z%#dba2{*Vec(H_s*l-r1UkTESC2y$W^YD#cGhw2=p8|(oIaz{xPZ`(riU|X=Hc_;P zf)BEXl2L5NHTFzm<|4shkCew0{a%IVZ)2`p1h5|(#3W6-IVM5jmU$+b65cvC2`*ab znRErhTggQqo$0j_lofrnyK-CUP7L7*MOIya>TM6pVMQG(UZA9Dz&_8p_@#5)xc3U`gioCnF{92F=ZGl+X8jO?C%|F{~RIOakI zbIiqrIwq$Y$ObvpiM!X{+;edpYk+GXYk-Mk4KVFv4KU~NnFp8)1Cv$!IxxGI|5B9? zjjZju?;UmL=<~i6U2G7RV`2w`v0%xIcY_rUXm+{Y1NXx)S zPSFTp=kiyc*009bts-iltAkS^9J?NXQ^qQA`i8G50ooB^jx7BMi*rd}TLjw@Y;3h~ z>;*4m%7tSe=YW$CP9mTUcfMfC?Ju1==nu3S(G0Q8B4+-_lUL z`Ly#QQ0gK^7p>18wdYsnrz6+2lQvn1K>+uh76o^sUoP8oivG&MsNd0_CRp)%_3PU% zT8`A6fe*_QaOTIsv2&Fj(6r*U)6QJTB}C57TyVriH*NI~ zPpC5xZ0bO|wMX3S#D!FoaO}hdCn+2|aha3m%TQwKs*RD7X~0ewtewitkyIw^-S;>} z^MKthSUZ2gF)iRU4kU&g$de*Y(Tf?5#DuP3iW>f2xXCrEP$;~=A{|_UMj8seoHe8C ztdG^%k-|Hnm9MWFmgD+L2>j-;5Sk5vUb$=F#x>@83VyVEYqvqrFRY)+`RTF?;e!!Y zk_ST7ow@ea>KSpCj@?Tv-P)mw&&St=g0u$(%s6~G*Pv@Zp^IW6bU*A8MnHBhtKt9| z{u@7K{*!c>Hyiw|qT3!t;8Y059z|k=?+7Vibf{-S%CBk*At8wF=b6BL*uBp#F5pMI zpZ5@|oBp(gl@2b%k6@h3)`M$G3&-s*YH-*5jstW-rMQ>ZfH+xhI^e*_up`xci9O&;iK++!B z@TW;Q_Q)2U{9{rHe^USHQ#IOjQxA<7&Mf||CV;AEFC%s3Nm`ylX;PHhMM0D{dP?aj z=;(Bjv`d6Y^8K*5lM3rdt8L-2~VefPNQKZP>Z00O-Z%iDre%%tsB&YepDLcfjNoYNVMp|Zpp?6MSxv|7j2 z^^^>`av@>LhJan2vbiWvS3~($QEpcoa4LjjR~wJRrKUo3(k{hqBtKfQwh;RM)2c+w zmWgsZ{7{|}j$Jc64hqIWNP&QYBI`nAAo2J<*Fb2Q!Y#nh9lWHjOVy=P G-~J!nOM&l-dmFN4vP*0U~D9YqXk){XPkw1NH$RaqqZ#hnK`)Vm}64Ww$@m4I{pHGE^2$TXQVqFe@P!YUzL`FuVSq( z+wpmmh1b@4H;d|>Yn_S`CdFEzDYnGuI1$98sCTkGuI>uRJL@+Z%h7Dl$bie7CdxBC z7rWd{k6w9SWKNA??DZLY-`JUs&54~7J2iGn^8WPPxF~J};*qX*%4(Sqf8b>L588;% z2uQ?Mir*^(oK!UPbPH?Kk1bG@Xk@CWX|xNpMLKeUnpp{(Q6?IP-EN^M^jx53Nu*Vi z$WWjsaHo;yhHs+LK8vV52=%+&)tuoK}kY`x?'!0xgO!nUfQYreOGD zwGxb4h)%O3+l*LDU8u@k#}4>b4~%2=`rIyP4q8pAOs}u0H>`=V8gZ-!j(s!Nv6$po zEE#BS%4C_IdXXvajLF!F>)(9fOg)uD7^@d}RRA7u zspb^dktOP{zkaoR=yK&mu5MdQDWcx*d?X#ei$2D$qo`Si0dRg!^%MLD&k5s`g2xD; z|K|!-R_v;LG><|#!<4F}YTma6Lp4a$y5(pSdvpBU#VeNAuUNit`IrmrGllmj zYOKrSQ7m#Dkc*w?^EembdhtyS7q{Fz_u3WLUA`>ecZX{X990=AEZ*&2OlnJO>tVBBl&aZ5F?T*8oN8KLuYa&cHNYNKZ?e}^uS>2`l@2L5 zi~cH7pbxgFlL4VpOOWPzz400~->F@rpEJ;gggRAUx?JsGV&}E$8z(Ib`YV-*%qGa} zOV_GPp_7UP=}gq?RV&173;(TMGqB(~^}VmPJ{h3(iE{owmj5TQOy8j1uIRXVDHWm( z@do~rutownoxLp_SzDrjZvRt$+PpRe6G;W_v-^ zW8YP?JlcMrHW|2R+wDQp@TSvAA0%B=wl_%H?~#h3OSRqZQA$9WK)#_0i!zs(?F}RD z&mp=F-=0HrjSO#M=ZUMHW+cshP%wR)*rcHv8Rt{yN+bKI8UzdnYd+7sLqw6MXYgly>a%xeP`E;vrIA0u6LbfnmC(eXLoLP%FcpI&TVctIN5{N zd=)o*+N2rFr=od_qq1jnsKSG?z~%-od)O@fo=&YE+c7CyD?IF8w@GR0@IHn zkt6Ol!(9^8M%;%CH|SPMjs55ljNSPQrxf*&mj$$SMfOD-N4w%-4R6drYz{-Hp{}ol zWcKDjI!TKjyhjzAagsT}O#Rk9YI;3l;557FqU__N1&r?hYD}gViZ8iWnLJjReo$^9 zibTLk_-fJxObze&YD}gt7sD;g-HuDoW{!B6k?o`UKkrpjj1$RRMtFON{q~Y@I3_cg zt0&9}+AN?%xSNIZ<+#B3*N+_Mi7UHnv}*xpP*I-2Rp&`}H}-u-IExrTHgbHEIU z3E5|ZyIF(k&-An4tOwML8x845=7=lEEecyH(7Ly0sLP-xW_OJZY%KsgFoa2R=L2e{ znO-ve!#mjI!OcGD$S_d9B$VrZPiC*{1$E)3Lh3V^mCx)@Gd%T~K32bqNUp9UnL$?< zwWxrup)QGGL$~MG(0;^F&-7g#-XQ_|_YO6)R01}<-wW8pk?nf+W;N|R;gCwV5eU+Q z;jJJuXvHm^YNnASGu#SZdQHrx#|8>Wl4)+4{vk=42_mx>%~-16eczkWGriJ|KX&?I z>XUZN?()Ml=(S@4g((&8Y-TSyUfg(=f3oqU-erc9r7@}G!g!ju_AC!IYzW$owyvw&&@fg9t^ zLv+U5pn238O0%EIE~Xb4?lceMrJ+&W3kF|G>JL{ZYqPe&6&QLD0a0fbGZR3;M&0(_# zl7;O>sknwBkUN5)>6mns=bUPzIgV7l9S^Ds#9L0a8}xG?0cWgK)`??U+9IxR&8?3g0(rku4!(`NH=dZ;9n6f(diN>=%T@~er`uWoO{FMkjJln zL_0e8fs3UYJ?~LE6E%c~S(EOfJ>h9giM2y^pq@Yv=+BAcf6Y7$gUg*}+xc1&l zeB>i#Fi-L0R1 zbMF3>KRQDX+DZg)r3;8ZOmnPdMF69RuQD3c`s|j-&hYocyjwF$ zrz+yz*x(Pt5$p=WRRA%1c#T0g!#^-8DCuzlE3RG#$DrdnG8hua>wU!ap$O--=Z%rb zSwRJHr;g@P_A;*MQ*4g@Vp(LCZg@U2Sx-%?w@>|N7*8bI(lNObck^>5!BfubwEeBD z(<=ufWoLpCS;z!Z_iQAu-V7^D9;v;pJ5II-Ro%icEjK{t{c@WBF=C=U-ikn7vMvRxB5X^e!qVbAkWR!`rJz z;3F##1}>0-{@6p?*EfP*1$4=ys=_!&gOy{}b#tWj3|RXQPu@NshrILpQNR;&m$HSUEerTOjCh?58 z*%q_s5W({xXZ*@fobp;xf4!(rIX~GN(xJ*zXU}*n8!r;39{ZzHjtHU(u>PrZG(Cwi zwEC>98~Efg)fFjDvkaaW?5@)|Pi9KW;Tp7?vGy{@Fljz2%zS!0CXI>0l62{`d!S^G zx;oPFB733Q+UPLmJHi zLqMpIz%GIILPzzOkKns5n{Yc5WsdZq+IP3tjq%aEHJAYS+KhB?87LOYZFHSW6fQ%C!qv5iK=#qFMB@Xyqjir&-YGMd zo0^z_#f+iwVIe{2DWxGK=|GGK3q1lK#E}dy&!qx5&5&Wg=u^lDXodv%dGF2Ox6|aw z)2Dzu9sMBq_GW=4W2%-S^zuGcb_u?&6rla86P&riv8N+&s^dooru?m1Rot<18Pa?; z{#afxhn`1J)6^=bbpw+y6Aies%gQ{YxnBtcLFg0d~d%Lx|fJ+v;BNk&kc$Nn;XBBpZbAmAAqr{_+=h5q%~jgDv<18 zWdxsAiXwXqf>SFTdrt*Ujd1J%4o2q%|Pe}4%0?kv?heImnf(eDV6lK@W&7>jiVTk;?$-vM3ax;k0CmmeFT4G#Esr* zyX%@~CK0YA=_}!nA!Zs!pGL~u`3W5xh}tHQ^ufRPTHGukZcj7)4k1KM!bc>+5lJ7B z3`G=?D_&&jOE-O~44R^6`2y3o45;bn!Q~=y&=(~aL%XGjoCHeulH`pdNpAU)2O$O224~nfDLGljpBtB|h z{&iq3iq&xx3!vP~zy`hI6`E8biK{?z7u!}tp}Rn)&|RQlWLZZ~LSLbY2^hK06Uwnn zp_N^O{>0~F`9_a?UZoASXwB~9!2Tr>j0*ZC5K|Z;D(Iag_z;j~ny{}h8r7K<29Hr$bkyizct?20KVSjC8g zdCqtd8`l{V>pW+C*>RjPqIu33DmycYTgQ(+WE9BPTK@XVK2^F^q6w&Ah5@RrhV(b%OzeM-9?AMtotLSs=cI;_5(!auc@Nb#bclKYjc zTf)gJP`FdYPqSnn*B2gfZp`^2Jj@$j9eEhbAI}{s2tGt*^*?0Q6n`8-7~?RRf$9NA>=&N<|=I|tL=or8(pIhgkD9L&YMbqBLHu&Rk) z0p>vah^n3t*)_25pVS>CbE;NSHg1T|#ve-toO_6aYs<^>~ckuUsz0*DWGyPo&_~2*)l5;8d{+ydJ{WqyX)RFh`b0gvE(Bu$_Xn z&$Yp+6OO&?1E*Rz_NfFo3E?CHp^Nk7B$)WbeEsHc)uaxHb&Ht&vs!T4g=4Suz-bkZ zoiO0c6^>mam=m8R!8f1a#C>-=lTL%!RuQuovk=4YJSb{>W+m8q!P;k1z~X%tVfk3@ zOi-HKmeWIw$Lz_M`Kic)G-<=~s2BpcZZnhM_hDsRgeBw9d|Pn zI$63vM&Rshg;cw6>}&<6RXBFGio!NJe5PQ}+ZZW74cNJYwey!blD~xAaJN%B2iUEG zwUZVcZUHj37^28aqHtcG#S~;Cq=R{B_&wqnl_uz*EKFpykK~3f79+SRoTFe zAE-%@;>V$xFH!ca#3hOl_{FdgjyD8)b+$(z{7{v}K!^@)8DbLpEVD1~H_R@Cj|9en z&`@A*-t`>|$L=9(%Ri^%X?&{{oSphG;_!{o9tsmZZ!wJ-dc>nlg7hK=aKSch`NzK_ zfbRH0l`Q~&i)gn83ph2xu?LIT<*TVZy75!Gz!d^Np%%i~hVUHw!5uf0_pc{_A02vb zh!MKuBf773Nr)Io$1;g7Aol222+)CVN%6-Xh!A!7w{>ETK3Sy&lAR)Hk413mgkz6I zaH@raaoFLV;EFlER1K0LZ zG=tMF9D6j2(pFC?ee#sLI>}ucI+P^X)Tgei@sPXX<8 z^pD2c^+6>0vQi|I;bG*YT7)Dj0O)rWLFc2N?A7+HE`PfUc;eJUnCdu&HDh}F3 ziRI;3fda!bsmb$p#N{L!JtAB$!uGTQVU#c)n^eNg*c_%}%yFiIbRsaAJ0$|{O!?FY zYKFe;_v#nLm8($pcBSL9R&jAU0R(!a$t(C-t27_|UuDxsfPOI9ofk~TP_dbXKUN1p zTCL+kNecPR_nAV%gbM+?>R4QqolBv8i)got2skyuv5Sbu;mhp~QA*nf_JW!aysXGa zLqt|5Wo&_fDD!LA&Ts}qi0ImA)S;*hgv@jNd5BMsb$ z+-JnloDj|SJfFi!Ik~lghcOgmu7_2-IzX~rblTNHI5&Zna`I~fxUC{*kNX@>%E=$} z%%rzY{LfKQPVp-lbTHKc_-5AuXcA7!$sgmQ2^&@x3aUsM$}3bjT#O7l QoSYgAtxiZ!