enne2/qwentts.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

api: derived codec left context, chunk width hoisted to qt_init

Browse Source 
The left context of the buffered chunked decode is no longer a caller
knob: it derives from the codec's own sliding window (2x144 frames),
placing the default decode at the residual floor of the split.
codec_chunk_sec moves from qt_tts_params to qt_init_params, resolved
once to frames at load. The mid-struct removal bumps the ABI to a
closed range [QT_ABI_MIN_VERSION, QT_ABI_VERSION] = [4, 4]; the probe
asserts both bounds reject through the range check.
This commit is contained in:
Pascal
2026-07-25 18:56:28 +02:00
parent 710a52af75
commit d03ffb97f9
8 changed files with 240 additions and 180 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/qwen-tts.cpp
+48 -52
View File
@@ -54,7 +54,6 @@ static void print_usage(const char * prog) {
" --ref-text <path> Transcript file for the reference (enables ICL clone mode)\n"
" --max-new <n> Max new audio frames (default: 2048)\n"
" --codec-chunk-dur <f> Codec decode chunk duration in seconds (default: 24.0)\n"
" --codec-left-dur <f> Codec decode left context duration in seconds (default: 2.0)\n"
" --stream-by-line Flush synthesis at each newline, one WAV header per line (-o '-')\n\n"
"Sampling:\n"
" --seed <int> Sampling seed (default: -1 for random)\n"
@@ -101,7 +100,6 @@ struct Args {
bool clamp_fp16;
bool stream_by_line;
float codec_chunk_sec;
float codec_left_context_sec;
};
// Read all of stdin into a string. Binary mode on Windows so UTF-16 input
@@ -180,25 +178,26 @@ static bool read_text_file(const char * path, std::string & out) {
}
static bool parse_args(int argc, char ** argv, Args & a) {
a = {};
a.lang = "auto";
a.format = "wav16";
a.max_new_tokens = 2048;
a.seed = -1;
a.do_sample = true;
a.temperature = 0.9f;
a.top_k = 50;
a.top_p = 1.0f;
a.repetition_penalty = 1.05f;
a.subtalker_do_sample = true;
a.subtalker_top_k = 50;
a.subtalker_top_p = 1.0f;
a.subtalker_temperature = 0.9f;
a.use_fa = true;
a.clamp_fp16 = false;
a.stream_by_line = false;
a.codec_chunk_sec = 24.0f;
a.codec_left_context_sec = 2.0f;
a = {};
a.lang = "auto";
a.format = "wav16";
a.max_new_tokens = 2048;
a.seed = -1;
a.do_sample = true;
a.temperature = 0.9f;
a.top_k = 50;
a.top_p = 1.0f;
a.repetition_penalty = 1.05f;
a.subtalker_do_sample = true;
a.subtalker_top_k = 50;
a.subtalker_top_p = 1.0f;
a.subtalker_temperature = 0.9f;
a.use_fa = true;
a.clamp_fp16 = false;
a.stream_by_line = false;
// Chunk sentinel : qt_init resolves a non positive value to the
// library default.
a.codec_chunk_sec = 0.0f;
for (int i = 1; i < argc; i++) {
const char * arg = argv[i];
if (std::strcmp(arg, "-h") == 0 || std::strcmp(arg, "--help") == 0) {
@@ -260,8 +259,6 @@ static bool parse_args(int argc, char ** argv, Args & a) {
a.stream_by_line = true;
} else if (std::strcmp(arg, "--codec-chunk-dur") == 0 && i + 1 < argc) {
a.codec_chunk_sec = (float) std::atof(argv[++i]);
} else if (std::strcmp(arg, "--codec-left-dur") == 0 && i + 1 < argc) {
a.codec_left_context_sec = (float) std::atof(argv[++i]);
} else if (std::strcmp(arg, "-o") == 0 && i + 1 < argc) {
a.out_wav = argv[++i];
} else {
@@ -279,10 +276,11 @@ static int run(const Args & a) {
// off the two GGUF paths and reports qt_last_error on failure.
qt_init_params iparams;
qt_init_default_params(&iparams);
iparams.talker_path = a.model;
iparams.codec_path = a.codec;
iparams.use_fa = a.use_fa;
iparams.clamp_fp16 = a.clamp_fp16;
iparams.talker_path = a.model;
iparams.codec_path = a.codec;
iparams.use_fa = a.use_fa;
iparams.clamp_fp16 = a.clamp_fp16;
iparams.codec_chunk_sec = a.codec_chunk_sec;
qt_context * q = qt_init(&iparams);
if (!q) {
@@ -391,31 +389,29 @@ static int run(const Args & a) {
// verbatim and resolved by qt_synthesize via std::random_device.
qt_tts_params params;
qt_tts_default_params(&params);
params.text = text;
params.lang = a.lang;
params.instruct = a.instruct;
params.speaker = a.speaker;
params.ref_audio_24k = ref_audio_24k;
params.ref_n_samples = ref_n_samples;
params.ref_text = ref_text;
params.ref_spk_emb = ref_spk_emb.empty() ? NULL : ref_spk_emb.data();
params.ref_spk_dim = (int) ref_spk_emb.size();
params.ref_codes = ref_codes.empty() ? NULL : ref_codes.data();
params.ref_T = ref_T;
params.seed = a.seed;
params.max_new_tokens = a.max_new_tokens;
params.do_sample = a.do_sample;
params.temperature = a.temperature;
params.top_k = a.top_k;
params.top_p = a.top_p;
params.repetition_penalty = a.repetition_penalty;
params.subtalker_do_sample = a.subtalker_do_sample;
params.subtalker_temperature = a.subtalker_temperature;
params.subtalker_top_k = a.subtalker_top_k;
params.subtalker_top_p = a.subtalker_top_p;
params.dump_dir = a.dump_dir;
params.codec_chunk_sec = a.codec_chunk_sec;
params.codec_left_context_sec = a.codec_left_context_sec;
params.text = text;
params.lang = a.lang;
params.instruct = a.instruct;
params.speaker = a.speaker;
params.ref_audio_24k = ref_audio_24k;
params.ref_n_samples = ref_n_samples;
params.ref_text = ref_text;
params.ref_spk_emb = ref_spk_emb.empty() ? NULL : ref_spk_emb.data();
params.ref_spk_dim = (int) ref_spk_emb.size();
params.ref_codes = ref_codes.empty() ? NULL : ref_codes.data();
params.ref_T = ref_T;
params.seed = a.seed;
params.max_new_tokens = a.max_new_tokens;
params.do_sample = a.do_sample;
params.temperature = a.temperature;
params.top_k = a.top_k;
params.top_p = a.top_p;
params.repetition_penalty = a.repetition_penalty;
params.subtalker_do_sample = a.subtalker_do_sample;
params.subtalker_temperature = a.subtalker_temperature;
params.subtalker_top_k = a.subtalker_top_k;
params.subtalker_top_p = a.subtalker_top_p;
params.dump_dir = a.dump_dir;
if (stream_to_stdout) {
wav_stream ws = {};
tools/tts-server.cpp
+13 -17
View File
@@ -52,8 +52,7 @@ static void print_usage(const char * prog) {
" --max-batch <n> Concurrent requests batched on the GPU (default: 1)\n"
" --no-fa Disable flash attention\n"
" --clamp-fp16 Clamp hidden states to FP16 range\n"
" --codec-chunk-dur <f> Codec decode chunk duration in seconds (default: 24.0)\n"
" --codec-left-dur <f> Codec decode left context duration in seconds (default: 2.0)\n",
" --codec-chunk-dur <f> Codec decode chunk duration in seconds, wav responses (default: 24.0)\n",
prog);
}
@@ -73,8 +72,9 @@ int main(int argc, char ** argv) {
bool use_fa = true;
bool clamp_fp16 = false;
int max_batch = 1;
float codec_chunk_dur = 24.0f;
float codec_left_dur = 2.0f;
// Chunk sentinel : qt_init resolves a non positive value to the
// library default.
float codec_chunk_dur = 0.0f;
for (int i = 1; i < argc; i++) {
const char * arg = argv[i];
@@ -98,8 +98,6 @@ int main(int argc, char ** argv) {
max_batch = std::atoi(argv[++i]);
} else if (!std::strcmp(arg, "--codec-chunk-dur") && i + 1 < argc) {
codec_chunk_dur = (float) std::atof(argv[++i]);
} else if (!std::strcmp(arg, "--codec-left-dur") && i + 1 < argc) {
codec_left_dur = (float) std::atof(argv[++i]);
} else if (!std::strcmp(arg, "--help") || !std::strcmp(arg, "-h")) {
print_usage(argv[0]);
return 0;
@@ -117,11 +115,12 @@ int main(int argc, char ** argv) {
struct qt_init_params iparams;
qt_init_default_params(&iparams);
iparams.talker_path = talker_path;
iparams.codec_path = codec_path;
iparams.use_fa = use_fa;
iparams.clamp_fp16 = clamp_fp16;
iparams.max_batch = max_batch;
iparams.talker_path = talker_path;
iparams.codec_path = codec_path;
iparams.use_fa = use_fa;
iparams.clamp_fp16 = clamp_fp16;
iparams.max_batch = max_batch;
iparams.codec_chunk_sec = codec_chunk_dur;
struct qt_context * q = qt_init(&iparams);
if (!q) {
@@ -220,14 +219,11 @@ int main(int argc, char ** argv) {
// the same name and injects the pre-extracted reference latents. A
// name matching neither is rejected instead of silently generating
// voiceless.
be.synthesize = [q, &lang, codec_chunk_dur, codec_left_dur](const tts_request & req, const tts_sink & sink,
std::string & err) -> int {
be.synthesize = [q, &lang](const tts_request & req, const tts_sink & sink, std::string & err) -> int {
struct qt_tts_params p;
qt_tts_default_params(&p);
p.text = req.input.c_str();
p.lang = lang.c_str();
p.codec_chunk_sec = codec_chunk_dur;
p.codec_left_context_sec = codec_left_dur;
p.text = req.input.c_str();
p.lang = lang.c_str();
// Copy the registered voice latents out under the lock: the
// synthesis may run for seconds while another connection