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
This commit is contained in:
parent
7695a53312
commit
080bbbe852
|
|
@ -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";
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue