Skip to content

whisper: detect multiple languages #3468

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

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
Open

whisper: detect multiple languages #3468

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
bfad386
Log language probs
isbee Oct 10, 2025
4f59ca3
Use sorted logits_id
isbee Oct 10, 2025
a5baab9
Remove redundant function call
isbee Oct 10, 2025
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
11 changes: 10 additions & 1 deletion src/whisper.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6805,7 +6805,16 @@ int whisper_full_with_state(
state->lang_id = lang_id;
params.language = whisper_lang_str(lang_id);

WHISPER_LOG_INFO("%s: auto-detected language: %s (p = %f)\n", __func__, params.language, probs[whisper_lang_id(params.language)]);
WHISPER_LOG_INFO("%s: auto-detected language: %s (p = %f)\n", __func__, params.language, probs[lang_id]);
const auto & sorted_logits_id = state->decoders[0].logits_id;
for (const auto & prob : sorted_logits_id) {
const auto lang_id = prob.second;
const char * lang_code = whisper_lang_str(lang_id);
Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

whisper_lang_str will be called N times. We might need to modify whisper_lang_str implementation from map 'iteration' to map 'lookup'.

WHISPER_LOG_INFO("%s: language prob: %s (p = %f)\n",
__func__,
lang_code,
prob.first);
}
if (params.detect_language) {
return 0;
}
Expand Down