Thanks to visit codestin.com
Credit goes to github.com

Skip to content

llama-tts : add '-o' option #12398

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 15, 2025
Merged

llama-tts : add '-o' option #12398

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1889,7 +1889,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params, const std::string & value) {
params.out_file = value;
}
).set_examples({LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_CVECTOR_GENERATOR, LLAMA_EXAMPLE_EXPORT_LORA}));
).set_examples({LLAMA_EXAMPLE_IMATRIX, LLAMA_EXAMPLE_CVECTOR_GENERATOR, LLAMA_EXAMPLE_EXPORT_LORA, LLAMA_EXAMPLE_TTS}));
add_opt(common_arg(
{"-ofreq", "--output-frequency"}, "N",
string_format("output the imatrix every N iterations (default: %d)", params.n_out_freq),
Expand Down
21 changes: 12 additions & 9 deletions examples/tts/tts.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -87,11 +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;
Expand All @@ -108,7 +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) {
Expand Down Expand Up @@ -536,6 +536,7 @@ static std::string audio_data_from_speaker(json speaker, const outetts_version t
int main(int argc, char ** argv) {
common_params params;

params.out_file = "output.wav";
params.prompt = "";

params.n_predict = 4096;
Expand Down Expand Up @@ -1060,8 +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
Expand All @@ -1072,11 +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;
}
Loading