From 080bbbe85230f624f0b52127f1ae1218247989f9 Mon Sep 17 00:00:00 2001
From: Cappuccino <32430057+JingliangGao@users.noreply.github.com>
Date: Sat, 11 Jul 2026 23:53:59 +0800
Subject: [PATCH] examples : Remove leading space from txt output (#3921)

* Fix #587: Remove leading space from txt output

The BPE tokenizer used by Whisper produces tokens with leading spaces,
causing each line in the txt output to start with an unwanted space.

This fix strips leading whitespace (spaces and tabs) from each segment
when writing to txt output files, improving the readability of the
transcription output.

Fixes: https://github.com/ggml-org/whisper.cpp/issues/587
---
 examples/cli/cli.cpp | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/examples/cli/cli.cpp b/examples/cli/cli.cpp
index e505bf0e1..c64976a56 100644
--- a/examples/cli/cli.cpp
+++ b/examples/cli/cli.cpp
@@ -465,7 +465,15 @@ static void output_txt(struct whisper_context * ctx, std::ofstream & fout, const
             speaker = estimate_diarization_speaker(pcmf32s, t0, t1);
         }
 
-        fout << speaker << text << "\n";
+        if (!speaker.empty()) {
+            fout << speaker << text;
+        } else {
+            while (*text == ' ' || *text == '\t') {
+                text++;
+            }
+            fout << text;
+        }
+        fout << "\n";
     }
 }