@fugood/llama.node 0.3.13 → 0.3.15

package/src/llama.cpp/examples/tts/tts.cpp

@@ -1,10 +1,11 @@
+#define _USE_MATH_DEFINES // For M_PI on MSVC
+
 #include "arg.h"
 #include "common.h"
 #include "sampling.h"
 #include "log.h"
 #include "llama.h"
-
-#define _USE_MATH_DEFINES // For M_PI on MSVC
+#include "json.hpp"
 
 #include <algorithm>
 #include <cmath>
@@ -16,6 +17,13 @@
 #include <thread>
 #include <vector>
 
+using json = nlohmann::ordered_json;
+
+enum outetts_version {
+    OUTETTS_V0_2,
+    OUTETTS_V0_3,
+};
+
 //
 // Terminal utils
 //
@@ -79,11 +87,11 @@ struct wav_header {
     uint32_t data_size;
 };
 
-static void save_wav16(const std::string & fname, const std::vector<float> & data, int sample_rate) {
+static bool save_wav16(const std::string & fname, const std::vector<float> & data, int sample_rate) {
     std::ofstream file(fname, std::ios::binary);
     if (!file) {
-        LOG_ERR("%s: Failed to open file '%s' for writing", __func__, fname.c_str());
-        return;
+        LOG_ERR("%s: Failed to open file '%s' for writing.\n", __func__, fname.c_str());
+        return false;
     }
 
     wav_header header;
@@ -100,7 +108,7 @@ static void save_wav16(const std::string & fname, const std::vector<float> & dat
         file.write(reinterpret_cast<const char*>(&pcm_sample), sizeof(pcm_sample));
     }
 
-    file.close();
+    return file.good();
 }
 
 static void fill_hann_window(int length, bool periodic, float * output) {
@@ -371,7 +379,7 @@ static std::string replace_numbers_with_words(const std::string & input_text) {
 }
 
 // Based on: https://github.com/edwko/OuteTTS/blob/a613e79c489d8256dd657ea9168d78de75895d82/outetts/version/v1/prompt_processor.py#L39
-static std::string process_text(const std::string & text) {
+static std::string process_text(const std::string & text, const outetts_version tts_version = OUTETTS_V0_2) {
 
     // For now I skipped text romanization as I am unsure how to handle
     // uroman and MeCab implementations in C++
@@ -401,7 +409,8 @@ static std::string process_text(const std::string & text) {
         if (c == ' ') {
             prompt_clean += "<|text_sep|>";
     */
-    processed_text = std::regex_replace(processed_text, std::regex(R"(\s)"), "<|text_sep|>");
+    std::string separator = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|text_sep|>";
+    processed_text = std::regex_replace(processed_text, std::regex(R"(\s)"), separator);
 
     return processed_text;
 }
@@ -425,8 +434,8 @@ static void prompt_init(llama_tokens & prompt, const llama_vocab * vocab) {
     prompt_add(prompt, vocab, "<|im_start|>\n", true, true);
 }
 
-static std::vector<llama_token> prepare_guide_tokens(const llama_vocab * vocab, const std::string & str) {
-    const std::string& delimiter = "<|text_sep|>";
+static std::vector<llama_token> prepare_guide_tokens(const llama_vocab * vocab, const std::string & str, const outetts_version tts_version = OUTETTS_V0_2) {
+    const std::string& delimiter = (tts_version == OUTETTS_V0_3 ? "<|space|>" : "<|text_sep|>");
 
     std::vector<llama_token> result;
     size_t start = 0;
@@ -452,9 +461,82 @@ static std::vector<llama_token> prepare_guide_tokens(const llama_vocab * vocab,
     return result;
 }
 
+static json speaker_from_file(const std::string & speaker_file) {
+    std::ifstream file(speaker_file);
+    if (!file) {
+        LOG_ERR("%s: Failed to open file '%s' for reading\n", __func__, speaker_file.c_str());
+        return json();
+    }
+
+    json speaker = json::parse(file);
+    return speaker;
+}
+
+static outetts_version get_tts_version(llama_model *model, json speaker = json::object()) {
+    if (speaker.contains("version")) {
+        std::string version = speaker["version"].get<std::string>();
+        if (version == "0.2") {
+            return OUTETTS_V0_2;
+        } else if (version == "0.3") {
+            return OUTETTS_V0_3;
+        } else {
+            LOG_ERR("%s: Unsupported speaker version '%s'\n", __func__, version.c_str());
+        }
+    }
+
+    // Also could get version from model itself
+    const char *chat_template = llama_model_chat_template(model, nullptr);
+    if (chat_template && std::string(chat_template) == "outetts-0.3") {
+        return OUTETTS_V0_3;
+    }
+
+    // Use 0.2 as the default version
+    return OUTETTS_V0_2;
+}
+
+static std::string audio_text_from_speaker(json speaker, const outetts_version tts_version = OUTETTS_V0_2) {
+    std::string audio_text = "<|text_start|>";
+
+    if (tts_version == OUTETTS_V0_2 || tts_version == OUTETTS_V0_3) {
+        std::string separator = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|text_sep|>";
+        for (const auto &word : speaker["words"]) {
+            audio_text += word["word"].get<std::string>() + separator;
+        }
+    }
+
+    return audio_text;
+}
+
+static std::string audio_data_from_speaker(json speaker, const outetts_version tts_version = OUTETTS_V0_2) {
+    std::string audio_data = "<|audio_start|>\n";
+
+    if (tts_version == OUTETTS_V0_2 || tts_version == OUTETTS_V0_3) {
+        std::string code_start = (tts_version == OUTETTS_V0_3) ? "" : "<|code_start|>";
+        std::string code_end = (tts_version == OUTETTS_V0_3) ? "<|space|>" : "<|code_end|>";
+        for (const auto &word : speaker["words"]) {
+            std::string word_text = word["word"].get<std::string>();
+            double duration = word["duration"].get<double>();
+            std::vector<int> codes = word["codes"].get<std::vector<int>>();
+
+            // Create the audio output entry
+            std::ostringstream word_entry;
+            word_entry << word_text << "<|t_" << std::fixed << std::setprecision(2)
+                       << duration << "|>" + code_start;
+            for (const auto &Code : codes) {
+                word_entry << "<|" << Code << "|>";
+            }
+            word_entry << code_end << "\n";
+            audio_data += word_entry.str();
+        }
+    }
+
+    return audio_data;
+}
+
 int main(int argc, char ** argv) {
     common_params params;
 
+    params.out_file = "output.wav";
     params.prompt = "";
 
     params.n_predict = 4096;
@@ -523,34 +605,9 @@ int main(int argc, char ** argv) {
     std::vector<llama_token> codes;
     std::vector<llama_token> guide_tokens;
 
-    // process prompt and generate voice codes
-    {
-        LOG_INF("%s: constructing prompt ..\n", __func__);
-
-        std::vector<llama_token> prompt_inp;
-
-        prompt_init(prompt_inp, vocab);
-
-        prompt_add(prompt_inp, vocab, "<|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);
-
-        // convert the input text into the necessary format expected by OuteTTS
-        {
-            std::string prompt_clean = process_text(params.prompt);
-            if (params.vocoder.use_guide_tokens) {
-                guide_tokens = prepare_guide_tokens(vocab, prompt_clean);
-            }
-
-            LOG_INF("%s: prompt: '%s'\n", __func__, prompt_clean.c_str());
-
-            prompt_add(prompt_inp, vocab, prompt_clean, false, true);
-        }
-
-        prompt_add(prompt_inp, vocab, "<|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 default speaker profile is from: https://github.com/edwko/OuteTTS/blob/main/outetts/version/v1/default_speakers/en_male_1.json
+    std::string audio_text = "<|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|>";
+    std::string audio_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|>
@@ -582,117 +639,170 @@ it<|t_0.09|><|code_start|><|848|><|1366|><|395|><|1601|><|1513|><|593|><|1302|><
 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(vocab, voice_data, false, true);
-        printf("\n\n");
-        for (int i = 0; i < tmp.size(); ++i) {
-            printf("%d, ", tmp[i]);
+    // audio data for 0.3 version
+    outetts_version tts_version = get_tts_version(model_ttc);
+    if (tts_version == OUTETTS_V0_3) {
+        audio_text = std::regex_replace(audio_text, std::regex(R"(<\|text_sep\|>)"), "<|space|>");
+        audio_data = std::regex_replace(audio_data, std::regex(R"(<\|code_start\|>)"), "");
+        audio_data = std::regex_replace(audio_data, std::regex(R"(<\|code_end\|>)"), "<|space|>");
+    }
+
+    // load speaker if given
+    if (!params.vocoder.speaker_file.empty()) {
+        LOG_INF("%s: loading speaker ..\n", __func__);
+        json speaker = speaker_from_file(params.vocoder.speaker_file);
+        if (speaker.empty()) {
+            LOG_ERR("%s: Failed to load speaker file '%s'\n", __func__, params.vocoder.speaker_file.c_str());
+            return 1;
         }
-        printf("\n\n");
+        audio_text = audio_text_from_speaker(speaker, tts_version);
+        audio_data = audio_data_from_speaker(speaker, tts_version);
+    }
+
+    // process prompt and generate voice codes
+    {
+        LOG_INF("%s: constructing prompt ..\n", __func__);
+
+        std::vector<llama_token> prompt_inp;
+
+        prompt_init(prompt_inp, vocab);
+
+        prompt_add(prompt_inp, vocab, audio_text, false, true);
+
+        // convert the input text into the necessary format expected by OuteTTS
+        {
+            std::string prompt_clean = process_text(params.prompt, tts_version);
+            if (params.vocoder.use_guide_tokens) {
+                guide_tokens = prepare_guide_tokens(vocab, prompt_clean, tts_version);
+            }
+
+            LOG_INF("%s: prompt: '%s'\n", __func__, prompt_clean.c_str());
+
+            prompt_add(prompt_inp, vocab, prompt_clean, false, true);
+        }
+
+        prompt_add(prompt_inp, vocab, "<|text_end|>\n", false, true);
+
+        if (!params.vocoder.speaker_file.empty()) {
+            prompt_add(prompt_inp, vocab, audio_data, false, true);
+        } else {
+            // disabled to save time on tokenizing each time
+#if 1
+            const std::string voice_data = audio_data;
+
+            auto tmp = common_tokenize(vocab, voice_data, false, true);
+            printf("\n\n");
+            for (size_t i = 0; i < tmp.size(); ++i) {
+                printf("%d, ", tmp[i]);
+            }
+            printf("\n\n");
+            prompt_add(prompt_inp, tmp);
 #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,});
+            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
 
@@ -951,8 +1061,6 @@ lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|14
     }
 #endif
 
-    const std::string fname = "output.wav";
-
     const int n_sr = 24000; // sampling rate
 
     // zero out first 0.25 seconds
@@ -963,11 +1071,15 @@ lovely<|t_0.56|><|code_start|><|634|><|596|><|1766|><|1556|><|1306|><|1285|><|14
     LOG_INF("%s: time for spectral ops: %.3f ms\n", __func__, (ggml_time_us() - t_spec_start) / 1000.0f);
     LOG_INF("%s: total time:            %.3f ms\n", __func__, (ggml_time_us() - t_main_start) / 1000.0f);
 
-    save_wav16(fname, audio, n_sr);
+    int retval = 0;
 
-    LOG_INF("%s: audio written to file '%s'\n", __func__, fname.c_str());
+    if (save_wav16(params.out_file, audio, n_sr)) {
+        LOG_INF("%s: audio written to file '%s'\n", __func__, params.out_file.c_str());
+    } else {
+        retval = ENOENT;
+    }
 
     llama_backend_free();
 
-    return 0;
+    return retval;
 }

package/src/llama.cpp/ggml/CMakeLists.txt

@@ -102,9 +102,11 @@ endif()
 
 option(GGML_CPU_HBM          "ggml: use memkind for CPU HBM" OFF)
 option(GGML_CPU_AARCH64      "ggml: use runtime weight conversion of Q4_0 to Q4_X_X" ON)
+option(GGML_CPU_KLEIDIAI     "ggml: use KleidiAI optimized kernels if applicable" OFF)
 option(GGML_AVX              "ggml: enable AVX"              ${INS_ENB})
 option(GGML_AVX_VNNI         "ggml: enable AVX-VNNI"         OFF)
 option(GGML_AVX2             "ggml: enable AVX2"             ${INS_ENB})
+option(GGML_BMI2             "ggml: enable BMI2"             ${INS_ENB})
 option(GGML_AVX512           "ggml: enable AVX512F"          OFF)
 option(GGML_AVX512_VBMI      "ggml: enable AVX512-VBMI"      OFF)
 option(GGML_AVX512_VNNI      "ggml: enable AVX512-VNNI"      OFF)
@@ -121,6 +123,7 @@ endif()
 option(GGML_LASX             "ggml: enable lasx"             ON)
 option(GGML_LSX              "ggml: enable lsx"              ON)
 option(GGML_RVV              "ggml: enable rvv"              ON)
+option(GGML_VXE              "ggml: enable vxe"              ON)
 
 option(GGML_CPU_ALL_VARIANTS "ggml: build all variants of the CPU backend (requires GGML_BACKEND_DL)" OFF)
 set(GGML_CPU_ARM_ARCH "" CACHE STRING "ggml: CPU architecture for ARM")
@@ -150,12 +153,17 @@ set   (GGML_CUDA_PEER_MAX_BATCH_SIZE "128" CACHE STRING
                                             "ggml: max. batch size for using peer access")
 option(GGML_CUDA_NO_PEER_COPY               "ggml: do not use peer to peer copies"            OFF)
 option(GGML_CUDA_NO_VMM                     "ggml: do not try to use CUDA VMM"                OFF)
+option(GGML_CUDA_FA                         "ggml: compile ggml FlashAttention CUDA kernels"  ON)
 option(GGML_CUDA_FA_ALL_QUANTS              "ggml: compile all quants for FlashAttention"     OFF)
 option(GGML_CUDA_GRAPHS                     "ggml: use CUDA graphs (llama.cpp only)"          ${GGML_CUDA_GRAPHS_DEFAULT})
+set   (GGML_CUDA_COMPRESSION_MODE "size" CACHE STRING
+                                            "ggml: cuda link binary compression mode; requires cuda 12.8+")
+set_property(CACHE GGML_CUDA_COMPRESSION_MODE PROPERTY STRINGS "none;speed;balance;size")
 
 option(GGML_HIP                             "ggml: use HIP"                                   OFF)
 option(GGML_HIP_GRAPHS                      "ggml: use HIP graph, experimental, slow"         OFF)
 option(GGML_HIP_NO_VMM                      "ggml: do not try to use HIP VMM"                 ON)
+option(GGML_HIP_ROCWMMA_FATTN               "ggml: enable rocWMMA for FlashAttention"         OFF)
 option(GGML_HIP_UMA                         "ggml: use HIP unified memory architecture"       OFF)
 option(GGML_VULKAN                          "ggml: use Vulkan"                                OFF)
 option(GGML_VULKAN_CHECK_RESULTS            "ggml: run Vulkan op checks"                      OFF)
@@ -178,6 +186,7 @@ option(GGML_OPENMP                          "ggml: use OpenMP"
 option(GGML_RPC                             "ggml: use RPC"                                   OFF)
 option(GGML_SYCL                            "ggml: use SYCL"                                  OFF)
 option(GGML_SYCL_F16                        "ggml: use 16 bit floats for sycl calculations"   OFF)
+option(GGML_SYCL_GRAPH                      "ggml: enable graphs in the SYCL backend"         ON)
 set   (GGML_SYCL_TARGET "INTEL" CACHE STRING
                                             "ggml: sycl target device")
 set   (GGML_SYCL_DEVICE_ARCH "" CACHE STRING
@@ -187,6 +196,8 @@ option(GGML_OPENCL                          "ggml: use OpenCL"
 option(GGML_OPENCL_PROFILING                "ggml: use OpenCL profiling (increases overhead)" OFF)
 option(GGML_OPENCL_EMBED_KERNELS            "ggml: embed kernels"                             ON)
 option(GGML_OPENCL_USE_ADRENO_KERNELS       "ggml: use optimized kernels for Adreno"          ON)
+set   (GGML_OPENCL_TARGET_VERSION "300" CACHE STRING
+                                            "gmml: OpenCL API version to target")
 
 # toolchain for vulkan-shaders-gen
 set   (GGML_VULKAN_SHADERS_GEN_TOOLCHAIN "" CACHE FILEPATH "ggml: toolchain file for vulkan-shaders-gen")
@@ -209,6 +220,8 @@ set(THREADS_PREFER_PTHREAD_FLAG ON)
 
 find_package(Threads REQUIRED)
 
+include(GNUInstallDirs)
+
 #
 # build the library
 #
@@ -232,7 +245,6 @@ endif ()
 # install
 #
 
-include(GNUInstallDirs)
 include(CMakePackageConfigHelpers)
 
 # all public headers
@@ -243,6 +255,7 @@ set(GGML_PUBLIC_HEADERS
     include/ggml-backend.h
     include/ggml-blas.h
     include/ggml-cann.h
+    include/ggml-cpp.h
     include/ggml-cuda.h
     include/ggml-kompute.h
     include/ggml-opt.h

package/src/llama.cpp/ggml/cmake/common.cmake

@@ -0,0 +1,26 @@
+function(ggml_get_flags CCID CCVER)
+    set(C_FLAGS "")
+    set(CXX_FLAGS "")
+
+    if (CCID MATCHES "Clang")
+        set(C_FLAGS   -Wunreachable-code-break -Wunreachable-code-return)
+        set(CXX_FLAGS -Wunreachable-code-break -Wunreachable-code-return -Wmissing-prototypes -Wextra-semi)
+
+        if (
+            (CCID STREQUAL "Clang"      AND CCVER VERSION_GREATER_EQUAL 3.8.0) OR
+            (CCID STREQUAL "AppleClang" AND CCVER VERSION_GREATER_EQUAL 7.3.0)
+        )
+            list(APPEND C_FLAGS -Wdouble-promotion)
+        endif()
+    elseif (CCID STREQUAL "GNU")
+        set(C_FLAGS   -Wdouble-promotion)
+        set(CXX_FLAGS -Wno-array-bounds)
+
+        if (CCVER VERSION_GREATER_EQUAL 8.1.0)
+            list(APPEND CXX_FLAGS -Wextra-semi)
+        endif()
+    endif()
+
+    set(GF_C_FLAGS   ${C_FLAGS}   PARENT_SCOPE)
+    set(GF_CXX_FLAGS ${CXX_FLAGS} PARENT_SCOPE)
+endfunction()

package/src/llama.cpp/ggml/include/ggml-alloc.h

@@ -19,7 +19,7 @@ struct ggml_tallocr {
 };
 
 GGML_API struct ggml_tallocr ggml_tallocr_new(ggml_backend_buffer_t buffer);
-GGML_API void                ggml_tallocr_alloc(struct ggml_tallocr * talloc, struct ggml_tensor * tensor);
+GGML_API enum ggml_status    ggml_tallocr_alloc(struct ggml_tallocr * talloc, struct ggml_tensor * tensor);
 
 // Graph allocator
 /*