Skip to content

Support textless diarization in transcription details #584

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
0xShug0 merged 1 commit into from
Sep 16, 2026
Merged

Support textless diarization in transcription details #584

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
10 changes: 7 additions & 3 deletions app/server/runtime.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2695,7 +2695,11 @@ HttpResponse ServerState::run_transcription(
: run_model(model, request, busy_timeout_ms);
const auto & result = timed_result.result;
if (!result.text_output.has_value()) {
throw std::runtime_error("model result did not contain transcript text");
std::shared_lock<std::shared_mutex> metadata_lock(model.metadata_mutex);
// Diarization has no transcript, even when silence yields no speaker turns.
if (!detail || model.task.task != engine::runtime::VoiceTaskKind::Diarization) {
throw std::runtime_error("model result did not contain transcript text");
}
}
if (!request.audio_input.has_value()) {
throw std::runtime_error("transcription timing requires audio_input");
Expand All @@ -2710,8 +2714,8 @@ HttpResponse ServerState::run_transcription(
// discards them. This is the opt-in route that keeps them, so the shape stays
// a superset of the plain one: text first, timing last, details in between.
std::ostringstream out;
out << "{\"text\":" << json_quote(result.text_output->text);
if (!result.text_output->language.empty()) {
out << "{\"text\":" << (result.text_output ? json_quote(result.text_output->text) : "\"\"");
if (result.text_output && !result.text_output->language.empty()) {
out << ",\"language\":" << json_quote(result.text_output->language);
}
write_transcript_detail_fields(out, result, [&](const std::string & name) {
Expand Down
Loading