mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-27 20:04:35 +00:00
tts : receive input text and generate codes
This commit is contained in:
Georgi Gerganov
parent
211cdf7326
commit
ae368ceb64
@ -264,6 +264,25 @@ static std::vector<double> embd_to_audio(
|
||||
return audio;
|
||||
}
|
||||
|
||||
static void prompt_add(llama_tokens & prompt, llama_token token) {
|
||||
prompt.push_back(token);
|
||||
}
|
||||
|
||||
static void prompt_add(llama_tokens & prompt, const llama_tokens & tokens) {
|
||||
prompt.insert(prompt.end(), tokens.begin(), tokens.end());
|
||||
}
|
||||
|
||||
static void prompt_add(llama_tokens & prompt, const llama_model * model, const std::string & txt, bool add_special, bool parse_special) {
|
||||
auto tmp = common_tokenize(model, txt, add_special, parse_special);
|
||||
prompt_add(prompt, tmp);
|
||||
}
|
||||
|
||||
static void prompt_init(llama_tokens & prompt, const llama_model * model) {
|
||||
prompt.clear();
|
||||
|
||||
prompt_add(prompt, model, "<|im_start|>\n", true, true);
|
||||
}
|
||||
|
||||
int main(int argc, char ** argv) {
|
||||
common_params params;
|
||||
|
||||
@ -273,10 +292,18 @@ int main(int argc, char ** argv) {
|
||||
params.n_batch = 8192;
|
||||
params.n_ctx = 8192;
|
||||
|
||||
params.sampling.top_k = 128;
|
||||
params.sampling.penalty_repeat = 1.1;
|
||||
params.sampling.penalty_last_n = 8;
|
||||
params.sampling.samplers = { COMMON_SAMPLER_TYPE_TEMPERATURE, COMMON_SAMPLER_TYPE_TOP_K, };
|
||||
|
||||
if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_TTS, print_usage)) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
const int n_parallel = params.n_parallel;
|
||||
const int n_predict = params.n_predict;
|
||||
|
||||
common_init();
|
||||
|
||||
// init LLM
|
||||
@ -301,48 +328,371 @@ int main(int argc, char ** argv) {
|
||||
model_cts = llama_init_cts.model;
|
||||
ctx_cts = llama_init_cts.context;
|
||||
|
||||
std::vector<common_sampler *> smpl(n_parallel);
|
||||
for (int i = 0; i < n_parallel; ++i) {
|
||||
params.sampling.no_perf = (i != 0);
|
||||
params.sampling.seed = params.sampling.seed + 1;
|
||||
|
||||
smpl[i] = common_sampler_init(model_ttc, params.sampling);
|
||||
}
|
||||
|
||||
LOG_INF("%s: loading done\n", __func__);
|
||||
|
||||
const auto t_main_start = ggml_time_us();
|
||||
|
||||
std::vector<llama_token> codes = {198, 88225, 155856, 151669, 152205,
|
||||
153064, 152537, 153421, 153209, 152524, 151689, 152993, 152438, 152695,
|
||||
153091, 152945, 152829, 152534, 152934, 153020, 151997, 152263, 153010,
|
||||
153146, 152399, 153208, 152496, 151793, 152848, 152263, 152571, 153286,
|
||||
152227, 153300, 152934, 152263, 153208, 152263, 152965, 152430, 152296,
|
||||
153146, 152920, 152376, 152556, 153363, 151775, 152044, 152972, 152690,
|
||||
153379, 152368, 152233, 153422, 152490, 151996, 152022, 151694, 152061,
|
||||
153238, 152539, 153356, 152640, 153021, 153123, 151962, 153094, 151670,
|
||||
198, 20339, 13189, 155824, 151669, 152070, 152007, 152910, 151683,
|
||||
152000, 152373, 152760, 152046, 151735, 152334, 152394, 153073, 152908,
|
||||
151856, 151953, 153247, 153293, 151903, 153480, 153168, 152478, 153359,
|
||||
153429, 151905, 151678, 152567, 152411, 152165, 152556, 153075, 153424,
|
||||
151993, 152999, 153078, 152151, 152088, 153389, 152484, 151874, 151670,
|
||||
198, 285, 155784, 151669, 152226, 152126, 152638, 153215, 151729,
|
||||
152959, 153479, 153059, 151838, 151670, 198, 1782, 155783, 151669,
|
||||
153288, 153055, 153314, 152497, 152962, 152741, 152076, 153253, 151670,
|
||||
198, 471, 16488, 155825, 151669, 152060, 152916, 151893, 153469, 152501,
|
||||
152080, 152743, 151932, 153161, 152096, 152761, 152698, 153401, 153242,
|
||||
153336, 152441, 152838, 153467, 152706, 153496, 153310, 152422, 153360,
|
||||
153115, 152763, 151998, 152373, 153450, 152554, 151968, 153323, 152055,
|
||||
152468, 153111, 153358, 152813, 152010, 151770, 152823, 152960, 151670,
|
||||
198, 22627, 155823, 151669, 152814, 152366, 153484, 152931, 153441,
|
||||
152164, 152877, 152915, 153463, 151692, 152911, 152747, 152776, 151831,
|
||||
153449, 151882, 152975, 152031, 152513, 153150, 152448, 152667, 153133,
|
||||
153189, 152619, 153466, 152054, 152106, 153119, 152277, 152439, 153109,
|
||||
152997, 152141, 153154, 153256, 153311, 151922, 151670, 198, 1055,
|
||||
155781, 151669, 152633, 151850, 153060, 153270, 152560, 153348, 152729,
|
||||
151670, 198, 25312, 155803, 151669, 152521, 153403, 152561, 153337,
|
||||
153383, 152199, 153493, 153326, 151830, 152254, 152248, 152349, 152153,
|
||||
153007, 151823, 153037, 152575, 152457, 152406, 152592, 153116, 153365,
|
||||
153456, 151670, 198, 88225, 155817, 151669, 153271, 151925, 152218,
|
||||
152418, 152253, 153140, 151903, 153151, 152626, 152338, 152647, 153464,
|
||||
152785, 152768, 151711, 152037, 152033, 151804, 152216, 151701, 151855,
|
||||
152348, 152995, 152955, 152905, 152342, 152340, 153391, 153453, 152418,
|
||||
153415, 151990, 153083, 152884, 151670, 198, 151668, 198, 151645};
|
||||
std::vector<llama_token> codes;
|
||||
|
||||
// process prompt and generate voice codes
|
||||
{
|
||||
LOG_INF("%s: constructing prompt ..\n", __func__);
|
||||
|
||||
std::vector<llama_token> prompt_inp;
|
||||
|
||||
prompt_init(prompt_inp, model_ttc);
|
||||
|
||||
prompt_add(prompt_inp, model_ttc, "<|text_start|>the<|text_sep|>overall<|text_sep|>package<|text_sep|>from<|text_sep|>just<|text_sep|>two<|text_sep|>people<|text_sep|>is<|text_sep|>pretty<|text_sep|>remarkable<|text_sep|>sure<|text_sep|>i<|text_sep|>have<|text_sep|>some<|text_sep|>critiques<|text_sep|>about<|text_sep|>some<|text_sep|>of<|text_sep|>the<|text_sep|>gameplay<|text_sep|>aspects<|text_sep|>but<|text_sep|>its<|text_sep|>still<|text_sep|>really<|text_sep|>enjoyable<|text_sep|>and<|text_sep|>it<|text_sep|>looks<|text_sep|>lovely<|text_sep|>", false, true);
|
||||
|
||||
// TODO: not sure if this is correct
|
||||
{
|
||||
std::string prompt_user = params.prompt;
|
||||
std::string prompt_clean = "";
|
||||
//string_replace_all(prompt_user, " ", "<|text_sep|>");
|
||||
for (auto & c : prompt_user) {
|
||||
if (c == ' ') {
|
||||
prompt_clean += "<|text_sep|>";
|
||||
} else {
|
||||
if (isalpha(c)) {
|
||||
c = tolower(c);
|
||||
} else {
|
||||
continue;
|
||||
}
|
||||
prompt_clean += c;
|
||||
}
|
||||
}
|
||||
|
||||
prompt_add(prompt_inp, model_ttc, prompt_clean, false, true);
|
||||
}
|
||||
|
||||
prompt_add(prompt_inp, model_ttc, "<|text_end|>\n", false, true);
|
||||
|
||||
// disabled to save time on tokenizing each time
|
||||
// TODO: load voices from the json files
|
||||
#if 0
|
||||
const std::string voice_data = R"(<|audio_start|>
|
||||
the<|t_0.08|><|code_start|><|257|><|740|><|636|><|913|><|788|><|1703|><|code_end|>
|
||||
overall<|t_0.36|><|code_start|><|127|><|201|><|191|><|774|><|700|><|532|><|1056|><|557|><|798|><|298|><|1741|><|747|><|1662|><|1617|><|1702|><|1527|><|368|><|1588|><|1049|><|1008|><|1625|><|747|><|1576|><|728|><|1019|><|1696|><|1765|><|code_end|>
|
||||
package<|t_0.56|><|code_start|><|935|><|584|><|1319|><|627|><|1016|><|1491|><|1344|><|1117|><|1526|><|1040|><|239|><|1435|><|951|><|498|><|723|><|1180|><|535|><|789|><|1649|><|1637|><|78|><|465|><|1668|><|901|><|595|><|1675|><|117|><|1009|><|1667|><|320|><|840|><|79|><|507|><|1762|><|1508|><|1228|><|1768|><|802|><|1450|><|1457|><|232|><|639|><|code_end|>
|
||||
from<|t_0.19|><|code_start|><|604|><|782|><|1682|><|872|><|1532|><|1600|><|1036|><|1761|><|647|><|1554|><|1371|><|653|><|1595|><|950|><|code_end|>
|
||||
just<|t_0.25|><|code_start|><|1782|><|1670|><|317|><|786|><|1748|><|631|><|599|><|1155|><|1364|><|1524|><|36|><|1591|><|889|><|1535|><|541|><|440|><|1532|><|50|><|870|><|code_end|>
|
||||
two<|t_0.24|><|code_start|><|1681|><|1510|><|673|><|799|><|805|><|1342|><|330|><|519|><|62|><|640|><|1138|><|565|><|1552|><|1497|><|1552|><|572|><|1715|><|1732|><|code_end|>
|
||||
people<|t_0.39|><|code_start|><|593|><|274|><|136|><|740|><|691|><|633|><|1484|><|1061|><|1138|><|1485|><|344|><|428|><|397|><|1562|><|645|><|917|><|1035|><|1449|><|1669|><|487|><|442|><|1484|><|1329|><|1832|><|1704|><|600|><|761|><|653|><|269|><|code_end|>
|
||||
is<|t_0.16|><|code_start|><|566|><|583|><|1755|><|646|><|1337|><|709|><|802|><|1008|><|485|><|1583|><|652|><|10|><|code_end|>
|
||||
pretty<|t_0.32|><|code_start|><|1818|><|1747|><|692|><|733|><|1010|><|534|><|406|><|1697|><|1053|><|1521|><|1355|><|1274|><|816|><|1398|><|211|><|1218|><|817|><|1472|><|1703|><|686|><|13|><|822|><|445|><|1068|><|code_end|>
|
||||
remarkable<|t_0.68|><|code_start|><|230|><|1048|><|1705|><|355|><|706|><|1149|><|1535|><|1787|><|1356|><|1396|><|835|><|1583|><|486|><|1249|><|286|><|937|><|1076|><|1150|><|614|><|42|><|1058|><|705|><|681|><|798|><|934|><|490|><|514|><|1399|><|572|><|1446|><|1703|><|1346|><|1040|><|1426|><|1304|><|664|><|171|><|1530|><|625|><|64|><|1708|><|1830|><|1030|><|443|><|1509|><|1063|><|1605|><|1785|><|721|><|1440|><|923|><|code_end|>
|
||||
sure<|t_0.36|><|code_start|><|792|><|1780|><|923|><|1640|><|265|><|261|><|1525|><|567|><|1491|><|1250|><|1730|><|362|><|919|><|1766|><|543|><|1|><|333|><|113|><|970|><|252|><|1606|><|133|><|302|><|1810|><|1046|><|1190|><|1675|><|code_end|>
|
||||
i<|t_0.08|><|code_start|><|123|><|439|><|1074|><|705|><|1799|><|637|><|code_end|>
|
||||
have<|t_0.16|><|code_start|><|1509|><|599|><|518|><|1170|><|552|><|1029|><|1267|><|864|><|419|><|143|><|1061|><|0|><|code_end|>
|
||||
some<|t_0.16|><|code_start|><|619|><|400|><|1270|><|62|><|1370|><|1832|><|917|><|1661|><|167|><|269|><|1366|><|1508|><|code_end|>
|
||||
critiques<|t_0.60|><|code_start|><|559|><|584|><|1163|><|1129|><|1313|><|1728|><|721|><|1146|><|1093|><|577|><|928|><|27|><|630|><|1080|><|1346|><|1337|><|320|><|1382|><|1175|><|1682|><|1556|><|990|><|1683|><|860|><|1721|><|110|><|786|><|376|><|1085|><|756|><|1523|><|234|><|1334|><|1506|><|1578|><|659|><|612|><|1108|><|1466|><|1647|><|308|><|1470|><|746|><|556|><|1061|><|code_end|>
|
||||
about<|t_0.29|><|code_start|><|26|><|1649|><|545|><|1367|><|1263|><|1728|><|450|><|859|><|1434|><|497|><|1220|><|1285|><|179|><|755|><|1154|><|779|><|179|><|1229|><|1213|><|922|><|1774|><|1408|><|code_end|>
|
||||
some<|t_0.23|><|code_start|><|986|><|28|><|1649|><|778|><|858|><|1519|><|1|><|18|><|26|><|1042|><|1174|><|1309|><|1499|><|1712|><|1692|><|1516|><|1574|><|code_end|>
|
||||
of<|t_0.07|><|code_start|><|197|><|716|><|1039|><|1662|><|64|><|code_end|>
|
||||
the<|t_0.08|><|code_start|><|1811|><|1568|><|569|><|886|><|1025|><|1374|><|code_end|>
|
||||
gameplay<|t_0.48|><|code_start|><|1269|><|1092|><|933|><|1362|><|1762|><|1700|><|1675|><|215|><|781|><|1086|><|461|><|838|><|1022|><|759|><|649|><|1416|><|1004|><|551|><|909|><|787|><|343|><|830|><|1391|><|1040|><|1622|><|1779|><|1360|><|1231|><|1187|><|1317|><|76|><|997|><|989|><|978|><|737|><|189|><|code_end|>
|
||||
aspects<|t_0.56|><|code_start|><|1423|><|797|><|1316|><|1222|><|147|><|719|><|1347|><|386|><|1390|><|1558|><|154|><|440|><|634|><|592|><|1097|><|1718|><|712|><|763|><|1118|><|1721|><|1311|><|868|><|580|><|362|><|1435|><|868|><|247|><|221|><|886|><|1145|><|1274|><|1284|><|457|><|1043|><|1459|><|1818|><|62|><|599|><|1035|><|62|><|1649|><|778|><|code_end|>
|
||||
but<|t_0.20|><|code_start|><|780|><|1825|><|1681|><|1007|><|861|><|710|><|702|><|939|><|1669|><|1491|><|613|><|1739|><|823|><|1469|><|648|><|code_end|>
|
||||
its<|t_0.09|><|code_start|><|92|><|688|><|1623|><|962|><|1670|><|527|><|599|><|code_end|>
|
||||
still<|t_0.27|><|code_start|><|636|><|10|><|1217|><|344|><|713|><|957|><|823|><|154|><|1649|><|1286|><|508|><|214|><|1760|><|1250|><|456|><|1352|><|1368|><|921|><|615|><|5|><|code_end|>
|
||||
really<|t_0.36|><|code_start|><|55|><|420|><|1008|><|1659|><|27|><|644|><|1266|><|617|><|761|><|1712|><|109|><|1465|><|1587|><|503|><|1541|><|619|><|197|><|1019|><|817|><|269|><|377|><|362|><|1381|><|507|><|1488|><|4|><|1695|><|code_end|>
|
||||
enjoyable<|t_0.49|><|code_start|><|678|><|501|><|864|><|319|><|288|><|1472|><|1341|><|686|><|562|><|1463|><|619|><|1563|><|471|><|911|><|730|><|1811|><|1006|><|520|><|861|><|1274|><|125|><|1431|><|638|><|621|><|153|><|876|><|1770|><|437|><|987|><|1653|><|1109|><|898|><|1285|><|80|><|593|><|1709|><|843|><|code_end|>
|
||||
and<|t_0.15|><|code_start|><|1285|><|987|><|303|><|1037|><|730|><|1164|><|502|><|120|><|1737|><|1655|><|1318|><|code_end|>
|
||||
it<|t_0.09|><|code_start|><|848|><|1366|><|395|><|1601|><|1513|><|593|><|1302|><|code_end|>
|
||||
looks<|t_0.27|><|code_start|><|1281|><|1266|><|1755|><|572|><|248|><|1751|><|1257|><|695|><|1380|><|457|><|659|><|585|><|1315|><|1105|><|1776|><|736|><|24|><|736|><|654|><|1027|><|code_end|>
|
||||
lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|1481|><|1721|><|1123|><|438|><|1246|><|1251|><|795|><|659|><|1381|><|1658|><|217|><|1772|><|562|><|952|><|107|><|1129|><|1112|><|467|><|550|><|1079|><|840|><|1615|><|1469|><|1380|><|168|><|917|><|836|><|1827|><|437|><|583|><|67|><|595|><|1087|><|1646|><|1493|><|1677|><|code_end|>)";
|
||||
|
||||
auto tmp = common_tokenize(model_ttc, voice_data, false, true);
|
||||
printf("\n\n");
|
||||
for (int i = 0; i < tmp.size(); ++i) {
|
||||
printf("%d, ", tmp[i]);
|
||||
}
|
||||
printf("\n\n");
|
||||
#else
|
||||
prompt_add(prompt_inp, llama_tokens {
|
||||
151667, 198, 1782, 155780, 151669, 151929, 152412, 152308, 152585,
|
||||
152460, 153375, 151670, 198, 74455, 155808, 151669, 151799,
|
||||
151873, 151863, 152446, 152372, 152204, 152728, 152229, 152470,
|
||||
151970, 153413, 152419, 153334, 153289, 153374, 153199, 152040,
|
||||
153260, 152721, 152680, 153297, 152419, 153248, 152400, 152691,
|
||||
153368, 153437, 151670, 198, 1722, 155828, 151669, 152607,
|
||||
152256, 152991, 152299, 152688, 153163, 153016, 152789, 153198,
|
||||
152712, 151911, 153107, 152623, 152170, 152395, 152852, 152207,
|
||||
152461, 153321, 153309, 151750, 152137, 153340, 152573, 152267,
|
||||
153347, 151789, 152681, 153339, 151992, 152512, 151751, 152179,
|
||||
153434, 153180, 152900, 153440, 152474, 153122, 153129, 151904,
|
||||
152311, 151670, 198, 1499, 155791, 151669, 152276, 152454,
|
||||
153354, 152544, 153204, 153272, 152708, 153433, 152319, 153226,
|
||||
153043, 152325, 153267, 152622, 151670, 198, 4250, 155797,
|
||||
151669, 153454, 153342, 151989, 152458, 153420, 152303, 152271,
|
||||
152827, 153036, 153196, 151708, 153263, 152561, 153207, 152213,
|
||||
152112, 153204, 151722, 152542, 151670, 198, 19789, 155796,
|
||||
151669, 153353, 153182, 152345, 152471, 152477, 153014, 152002,
|
||||
152191, 151734, 152312, 152810, 152237, 153224, 153169, 153224,
|
||||
152244, 153387, 153404, 151670, 198, 16069, 155811, 151669,
|
||||
152265, 151946, 151808, 152412, 152363, 152305, 153156, 152733,
|
||||
152810, 153157, 152016, 152100, 152069, 153234, 152317, 152589,
|
||||
152707, 153121, 153341, 152159, 152114, 153156, 153001, 153504,
|
||||
153376, 152272, 152433, 152325, 151941, 151670, 198, 285,
|
||||
155788, 151669, 152238, 152255, 153427, 152318, 153009, 152381,
|
||||
152474, 152680, 152157, 153255, 152324, 151682, 151670, 198,
|
||||
32955, 155804, 151669, 153490, 153419, 152364, 152405, 152682,
|
||||
152206, 152078, 153369, 152725, 153193, 153027, 152946, 152488,
|
||||
153070, 151883, 152890, 152489, 153144, 153375, 152358, 151685,
|
||||
152494, 152117, 152740, 151670, 198, 37448, 480, 155840, 151669,
|
||||
151902, 152720, 153377, 152027, 152378, 152821, 153207, 153459,
|
||||
153028, 153068, 152507, 153255, 152158, 152921, 151958, 152609,
|
||||
152748, 152822, 152286, 151714, 152730, 152377, 152353, 152470,
|
||||
152606, 152162, 152186, 153071, 152244, 153118, 153375, 153018,
|
||||
152712, 153098, 152976, 152336, 151843, 153202, 152297, 151736,
|
||||
153380, 153502, 152702, 152115, 153181, 152735, 153277, 153457,
|
||||
152393, 153112, 152595, 151670, 198, 19098, 155808, 151669,
|
||||
152464, 153452, 152595, 153312, 151937, 151933, 153197, 152239,
|
||||
153163, 152922, 153402, 152034, 152591, 153438, 152215, 151673,
|
||||
152005, 151785, 152642, 151924, 153278, 151805, 151974, 153482,
|
||||
152718, 152862, 153347, 151670, 198, 72, 155780, 151669, 151795,
|
||||
152111, 152746, 152377, 153471, 152309, 151670, 198, 19016,
|
||||
155788, 151669, 153181, 152271, 152190, 152842, 152224, 152701,
|
||||
152939, 152536, 152091, 151815, 152733, 151672, 151670, 198,
|
||||
14689, 155788, 151669, 152291, 152072, 152942, 151734, 153042,
|
||||
153504, 152589, 153333, 151839, 151941, 153038, 153180, 151670,
|
||||
198, 36996, 8303, 155832, 151669, 152231, 152256, 152835,
|
||||
152801, 152985, 153400, 152393, 152818, 152765, 152249, 152600,
|
||||
151699, 152302, 152752, 153018, 153009, 151992, 153054, 152847,
|
||||
153354, 153228, 152662, 153355, 152532, 153393, 151782, 152458,
|
||||
152048, 152757, 152428, 153195, 151906, 153006, 153178, 153250,
|
||||
152331, 152284, 152780, 153138, 153319, 151980, 153142, 152418,
|
||||
152228, 152733, 151670, 198, 9096, 155801, 151669, 151698,
|
||||
153321, 152217, 153039, 152935, 153400, 152122, 152531, 153106,
|
||||
152169, 152892, 152957, 151851, 152427, 152826, 152451, 151851,
|
||||
152901, 152885, 152594, 153446, 153080, 151670, 198, 14689,
|
||||
155795, 151669, 152658, 151700, 153321, 152450, 152530, 153191,
|
||||
151673, 151690, 151698, 152714, 152846, 152981, 153171, 153384,
|
||||
153364, 153188, 153246, 151670, 198, 1055, 155779, 151669,
|
||||
151869, 152388, 152711, 153334, 151736, 151670, 198, 1782,
|
||||
155780, 151669, 153483, 153240, 152241, 152558, 152697, 153046,
|
||||
151670, 198, 5804, 1363, 155820, 151669, 152941, 152764, 152605,
|
||||
153034, 153434, 153372, 153347, 151887, 152453, 152758, 152133,
|
||||
152510, 152694, 152431, 152321, 153088, 152676, 152223, 152581,
|
||||
152459, 152015, 152502, 153063, 152712, 153294, 153451, 153032,
|
||||
152903, 152859, 152989, 151748, 152669, 152661, 152650, 152409,
|
||||
151861, 151670, 198, 300, 7973, 155828, 151669, 153095, 152469,
|
||||
152988, 152894, 151819, 152391, 153019, 152058, 153062, 153230,
|
||||
151826, 152112, 152306, 152264, 152769, 153390, 152384, 152435,
|
||||
152790, 153393, 152983, 152540, 152252, 152034, 153107, 152540,
|
||||
151919, 151893, 152558, 152817, 152946, 152956, 152129, 152715,
|
||||
153131, 153490, 151734, 152271, 152707, 151734, 153321, 152450,
|
||||
151670, 198, 8088, 155792, 151669, 152452, 153497, 153353,
|
||||
152679, 152533, 152382, 152374, 152611, 153341, 153163, 152285,
|
||||
153411, 152495, 153141, 152320, 151670, 198, 1199, 155781,
|
||||
151669, 151764, 152360, 153295, 152634, 153342, 152199, 152271,
|
||||
151670, 198, 43366, 155799, 151669, 152308, 151682, 152889,
|
||||
152016, 152385, 152629, 152495, 151826, 153321, 152958, 152180,
|
||||
151886, 153432, 152922, 152128, 153024, 153040, 152593, 152287,
|
||||
151677, 151670, 198, 53660, 155808, 151669, 151727, 152092,
|
||||
152680, 153331, 151699, 152316, 152938, 152289, 152433, 153384,
|
||||
151781, 153137, 153259, 152175, 153213, 152291, 151869, 152691,
|
||||
152489, 151941, 152049, 152034, 153053, 152179, 153160, 151676,
|
||||
153367, 151670, 198, 268, 4123, 480, 155821, 151669, 152350,
|
||||
152173, 152536, 151991, 151960, 153144, 153013, 152358, 152234,
|
||||
153135, 152291, 153235, 152143, 152583, 152402, 153483, 152678,
|
||||
152192, 152533, 152946, 151797, 153103, 152310, 152293, 151825,
|
||||
152548, 153442, 152109, 152659, 153325, 152781, 152570, 152957,
|
||||
151752, 152265, 153381, 152515, 151670, 198, 437, 155787,
|
||||
151669, 152957, 152659, 151975, 152709, 152402, 152836, 152174,
|
||||
151792, 153409, 153327, 152990, 151670, 198, 275, 155781,
|
||||
151669, 152520, 153038, 152067, 153273, 153185, 152265, 152974,
|
||||
151670, 198, 94273, 155799, 151669, 152953, 152938, 153427,
|
||||
152244, 151920, 153423, 152929, 152367, 153052, 152129, 152331,
|
||||
152257, 152987, 152777, 153448, 152408, 151696, 152408, 152326,
|
||||
152699, 151670, 198, 385, 16239, 155828, 151669, 152306, 152268,
|
||||
153438, 153228, 152978, 152957, 153153, 153393, 152795, 152110,
|
||||
152918, 152923, 152467, 152331, 153053, 153330, 151889, 153444,
|
||||
152234, 152624, 151779, 152801, 152784, 152139, 152222, 152751,
|
||||
152512, 153287, 153141, 153052, 151840, 152589, 152508, 153499,
|
||||
152109, 152255, 151739, 152267, 152759, 153318, 153165, 153349,
|
||||
151670,});
|
||||
#endif
|
||||
|
||||
// print the prompt token-by-token
|
||||
|
||||
LOG("\n");
|
||||
|
||||
for (auto id : prompt_inp) {
|
||||
LOG("%s", common_token_to_piece(ctx_ttc, id).c_str());
|
||||
}
|
||||
|
||||
LOG_INF("%s: prompt size: %d\n", __func__, (int) prompt_inp.size());
|
||||
|
||||
LOG("\n");
|
||||
|
||||
// create a llama_batch
|
||||
// we use this object to submit token data for decoding
|
||||
llama_batch batch = llama_batch_init(std::max(prompt_inp.size(), (size_t) n_parallel), 0, n_parallel);
|
||||
|
||||
std::vector<llama_seq_id> seq_ids(n_parallel, 0);
|
||||
for (int32_t i = 0; i < n_parallel; ++i) {
|
||||
seq_ids[i] = i;
|
||||
}
|
||||
|
||||
// evaluate the initial prompt
|
||||
for (size_t i = 0; i < prompt_inp.size(); ++i) {
|
||||
common_batch_add(batch, prompt_inp[i], i, seq_ids, false);
|
||||
}
|
||||
GGML_ASSERT(batch.n_tokens == (int) prompt_inp.size());
|
||||
|
||||
// llama_decode will output logits only for the last token of the prompt
|
||||
batch.logits[batch.n_tokens - 1] = true;
|
||||
|
||||
if (llama_decode(ctx_ttc, batch) != 0) {
|
||||
LOG_ERR("%s: llama_decode() failed\n", __func__);
|
||||
return 1;
|
||||
}
|
||||
|
||||
if (n_parallel > 1) {
|
||||
LOG_INF("\n\n%s: generating %d sequences ...\n", __func__, n_parallel);
|
||||
}
|
||||
|
||||
llama_synchronize(ctx_ttc);
|
||||
|
||||
LOG_INF("%s: time for prompt: %.3f ms\n\n", __func__, (ggml_time_us() - t_main_start) / 1000.0f);
|
||||
|
||||
const auto t_dec_start = ggml_time_us();
|
||||
|
||||
// main loop
|
||||
|
||||
// remember the batch index of the last token for each parallel sequence
|
||||
// we need this to determine which logits to sample from
|
||||
std::vector<int32_t> i_batch(n_parallel, batch.n_tokens - 1);
|
||||
|
||||
int n_past = batch.n_tokens;
|
||||
int n_decode = 0;
|
||||
|
||||
while (n_decode <= n_predict) {
|
||||
// prepare the next batch
|
||||
common_batch_clear(batch);
|
||||
|
||||
// sample the next token for each parallel sequence / stream
|
||||
for (int32_t i = 0; i < n_parallel; ++i) {
|
||||
if (i_batch[i] < 0) {
|
||||
// the stream has already finished
|
||||
continue;
|
||||
}
|
||||
|
||||
const llama_token new_token_id = common_sampler_sample(smpl[i], ctx_ttc, i_batch[i]);
|
||||
|
||||
common_sampler_accept(smpl[i], new_token_id, true);
|
||||
|
||||
codes.push_back(new_token_id);
|
||||
|
||||
const auto * cands = common_sampler_get_candidates(smpl[i]);
|
||||
|
||||
// is it an end of generation? -> mark the stream as finished
|
||||
if (llama_token_is_eog(model_ttc, new_token_id) || n_decode == n_predict) {
|
||||
std::string reason;
|
||||
if (llama_token_is_eog(model_ttc, new_token_id)) {
|
||||
reason = "eos";
|
||||
} else {
|
||||
reason = "n_predict";
|
||||
}
|
||||
|
||||
i_batch[i] = -1;
|
||||
|
||||
LOG("\n");
|
||||
if (n_parallel > 1) {
|
||||
LOG_CNT("\n");
|
||||
LOG_INF("%s: stream %d finished at n_past = %d, reason = '%s'\n", __func__, i, n_past, reason.c_str());
|
||||
}
|
||||
|
||||
continue;
|
||||
}
|
||||
|
||||
{
|
||||
const float p = cands->data[cands->selected].p;
|
||||
|
||||
const int col = std::max(0, std::min((int) k_colors.size() - 1, (int) ((3*p)*float(k_colors.size()))));
|
||||
|
||||
LOG_CNT("%s%d%s", k_colors[col].c_str(), i, "\033[0m");
|
||||
//LOG_CNT("%d", i);
|
||||
}
|
||||
|
||||
i_batch[i] = batch.n_tokens;
|
||||
|
||||
// push this new token for next evaluation
|
||||
common_batch_add(batch, new_token_id, n_past, { i }, true);
|
||||
}
|
||||
|
||||
// all streams are finished
|
||||
if (batch.n_tokens == 0) {
|
||||
break;
|
||||
}
|
||||
|
||||
n_decode += 1;
|
||||
n_past += 1;
|
||||
|
||||
// evaluate the current batch with the transformer model
|
||||
if (llama_decode(ctx_ttc, batch)) {
|
||||
LOG_ERR("%s : failed to eval, return code %d\n", __func__, 1);
|
||||
return 1;
|
||||
}
|
||||
}
|
||||
|
||||
llama_batch_free(batch);
|
||||
|
||||
LOG("\n");
|
||||
LOG_INF("%s: time for decoder: %.3f ms\n", __func__, (ggml_time_us() - t_dec_start) / 1000.0f);
|
||||
}
|
||||
|
||||
//std::vector<llama_token> codes = {198, 88225, 155856, 151669, 152205,
|
||||
// 153064, 152537, 153421, 153209, 152524, 151689, 152993, 152438, 152695,
|
||||
// 153091, 152945, 152829, 152534, 152934, 153020, 151997, 152263, 153010,
|
||||
// 153146, 152399, 153208, 152496, 151793, 152848, 152263, 152571, 153286,
|
||||
// 152227, 153300, 152934, 152263, 153208, 152263, 152965, 152430, 152296,
|
||||
// 153146, 152920, 152376, 152556, 153363, 151775, 152044, 152972, 152690,
|
||||
// 153379, 152368, 152233, 153422, 152490, 151996, 152022, 151694, 152061,
|
||||
// 153238, 152539, 153356, 152640, 153021, 153123, 151962, 153094, 151670,
|
||||
// 198, 20339, 13189, 155824, 151669, 152070, 152007, 152910, 151683,
|
||||
// 152000, 152373, 152760, 152046, 151735, 152334, 152394, 153073, 152908,
|
||||
// 151856, 151953, 153247, 153293, 151903, 153480, 153168, 152478, 153359,
|
||||
// 153429, 151905, 151678, 152567, 152411, 152165, 152556, 153075, 153424,
|
||||
// 151993, 152999, 153078, 152151, 152088, 153389, 152484, 151874, 151670,
|
||||
// 198, 285, 155784, 151669, 152226, 152126, 152638, 153215, 151729,
|
||||
// 152959, 153479, 153059, 151838, 151670, 198, 1782, 155783, 151669,
|
||||
// 153288, 153055, 153314, 152497, 152962, 152741, 152076, 153253, 151670,
|
||||
// 198, 471, 16488, 155825, 151669, 152060, 152916, 151893, 153469, 152501,
|
||||
// 152080, 152743, 151932, 153161, 152096, 152761, 152698, 153401, 153242,
|
||||
// 153336, 152441, 152838, 153467, 152706, 153496, 153310, 152422, 153360,
|
||||
// 153115, 152763, 151998, 152373, 153450, 152554, 151968, 153323, 152055,
|
||||
// 152468, 153111, 153358, 152813, 152010, 151770, 152823, 152960, 151670,
|
||||
// 198, 22627, 155823, 151669, 152814, 152366, 153484, 152931, 153441,
|
||||
// 152164, 152877, 152915, 153463, 151692, 152911, 152747, 152776, 151831,
|
||||
// 153449, 151882, 152975, 152031, 152513, 153150, 152448, 152667, 153133,
|
||||
// 153189, 152619, 153466, 152054, 152106, 153119, 152277, 152439, 153109,
|
||||
// 152997, 152141, 153154, 153256, 153311, 151922, 151670, 198, 1055,
|
||||
// 155781, 151669, 152633, 151850, 153060, 153270, 152560, 153348, 152729,
|
||||
// 151670, 198, 25312, 155803, 151669, 152521, 153403, 152561, 153337,
|
||||
// 153383, 152199, 153493, 153326, 151830, 152254, 152248, 152349, 152153,
|
||||
// 153007, 151823, 153037, 152575, 152457, 152406, 152592, 153116, 153365,
|
||||
// 153456, 151670, 198, 88225, 155817, 151669, 153271, 151925, 152218,
|
||||
// 152418, 152253, 153140, 151903, 153151, 152626, 152338, 152647, 153464,
|
||||
// 152785, 152768, 151711, 152037, 152033, 151804, 152216, 151701, 151855,
|
||||
// 152348, 152995, 152955, 152905, 152342, 152340, 153391, 153453, 152418,
|
||||
// 153415, 151990, 153083, 152884, 151670, 198, 151668, 198, 151645};
|
||||
|
||||
{
|
||||
const std::string inp_txt = common_detokenize(ctx_ttc, codes, true);
|
||||
LOG_INF("prompt: '%s'\n", inp_txt.c_str());
|
||||
LOG_INF("%s: prompt size: %d\n", __func__, (int) codes.size());
|
||||
|
||||
LOG("\n");
|
||||
LOG_INF("codes: '%s'\n", inp_txt.c_str());
|
||||
LOG_INF("%s: codes size: %d\n", __func__, (int) codes.size());
|
||||
}
|
||||
|
||||
// remove all non-audio tokens (i.e. < 151672 || > 155772)
|
||||
@ -350,8 +700,8 @@ int main(int argc, char ** argv) {
|
||||
|
||||
{
|
||||
const std::string inp_txt = common_detokenize(ctx_ttc, codes, true);
|
||||
LOG_INF("prompt audio: '%s'\n", inp_txt.c_str());
|
||||
LOG_INF("%s: prompt audio size: %d\n", __func__, (int) codes.size());
|
||||
LOG_INF("codes audio: '%s'\n", inp_txt.c_str());
|
||||
LOG_INF("%s: codes audio size: %d\n", __func__, (int) codes.size());
|
||||
}
|
||||
|
||||
for (auto & token : codes) {
|
||||
@ -362,7 +712,6 @@ int main(int argc, char ** argv) {
|
||||
|
||||
llama_batch batch = llama_batch_init(codes.size(), 0, 1);
|
||||
|
||||
// evaluate the initial prompt
|
||||
for (size_t i = 0; i < codes.size(); ++i) {
|
||||
common_batch_add(batch, codes[i], i, { 0 }, true); // TODO: all logits?
|
||||
}
|
||||
@ -379,11 +728,11 @@ int main(int argc, char ** argv) {
|
||||
|
||||
const auto t_spec_start = ggml_time_us();
|
||||
|
||||
// spectral operations
|
||||
// TODO: not optimized at all
|
||||
const int n_embd = llama_n_embd(model_cts);
|
||||
const float * embd = llama_get_embeddings(ctx_cts);
|
||||
|
||||
// spectral operations
|
||||
// TODO: not optimized at all
|
||||
auto audio = embd_to_audio(embd, codes, n_embd, params.cpuparams.n_threads);
|
||||
|
||||
const std::string fname = "output.wav";
|
||||
|
||||
Loading…
Reference in New Issue
Block a user