From: Bjarke Viksøe <redacted>
Date: Sun, 10 May 2026 14:24:12 +0000 (+0200)
Subject: whisper : fix incorrect timestamps, usually near silences (#2279)
X-Git-Tag: upstream/1.9.2~477
X-Git-Url: https://git.djapps.eu/?a=commitdiff_plain;h=c33c5618b72bb345df029b730b36bc0e369845a3;p=pkg%2Fggml%2Fsources%2Fwhisper.cpp

whisper : fix incorrect timestamps, usually near silences (#2279)

* Incorrect timetstamps

Fixes #2271

- Adds consecutive timestamps after end of last segment as the new starting ts
- Add these timestamp to output when "print-special" enabled
- Fixes fflush usage in live reporting

I was not able to test this with the special "token_timestamps" option.

* Skip initial timestamp
---

diff --git a/src/whisper.cpp b/src/whisper.cpp
index 2f356da0..6176d21f 100644
--- a/src/whisper.cpp
+++ b/src/whisper.cpp
@@ -7659,11 +7659,14 @@ int whisper_full_with_state(
                             }
                         }
                         text = "";
-                        while (i < (int) tokens_cur.size() && tokens_cur[i].id > whisper_token_beg(ctx)) {
+                        t0 = t1;
+                        while (i + 1 < (int) tokens_cur.size() && tokens_cur[i + 1].id > whisper_token_beg(ctx)) {
                             i++;
+                            if (params.print_special) {
+                                text += whisper_token_to_str(ctx, tokens_cur[i].id);
+                            }
+                            t0 = seek + 2 * (tokens_cur[i].tid - whisper_token_beg(ctx));
                         }
-                        i--;
-                        t0 = t1;
                         i0 = i + 1;
                         speaker_turn_next = false;
                     }
@@ -7680,8 +7683,8 @@ int whisper_full_with_state(
                             printf("[%s --> %s]  %s\n", to_timestamp(tt0).c_str(), to_timestamp(tt1).c_str(), text.c_str());
                         } else {
                             printf("%s", text.c_str());
-                            fflush(stdout);
                         }
+                        fflush(stdout);
                     }
 
                     result_all.push_back({ tt0, tt1, text, state->no_speech_prob, {}, speaker_turn_next });