diff --git a/examples/server/server.cpp b/examples/server/server.cpp index f709225bd81..965ba242c9a 100644 --- a/examples/server/server.cpp +++ b/examples/server/server.cpp @@ -919,6 +919,11 @@ int main(int argc, char ** argv) { } else if (params.response_format == vjson_format) { /* try to match openai/whisper's Python format */ std::string results = output_str(ctx, params, pcmf32s); + + // Get language probabilities + std::vector lang_probs(whisper_lang_max_id() + 1, 0.0f); + const auto detected_lang_id = whisper_lang_auto_detect(ctx, 0, params.n_threads, lang_probs.data()); + json jres = json{ {"task", params.translate ? "translate" : "transcribe"}, {"language", whisper_lang_str_full(whisper_full_lang_id(ctx))}, @@ -926,6 +931,22 @@ int main(int argc, char ** argv) { {"text", results}, {"segments", json::array()} }; + + // Always include language detection info + json lang_info = json::object(); + // Include the probability of the detected language + lang_info["probability"] = lang_probs[detected_lang_id]; + + // Add all language probabilities + json all_lang_probs = json::object(); + for (int i = 0; i <= whisper_lang_max_id(); ++i) { + if (lang_probs[i] > 0.001f) { // Only include non-negligible probabilities + all_lang_probs[whisper_lang_str(i)] = lang_probs[i]; + } + } + lang_info["language_probabilities"] = all_lang_probs; + jres["language_detection"] = lang_info; + const int n_segments = whisper_full_n_segments(ctx); for (int i = 0; i < n_segments; ++i) {