avfilter/af_whisper: fix broken output for multibyte character

text + 1 can break a multibyte character, e.g., Chinese in UTF-8.
There is no space at the beginning in this case.
This commit is contained in:
Zhao Zhili
2025-08-15 20:39:49 +08:00
committed by michaelni
parent 30e6956920
commit 1d06e8ddcd

View File

@@ -215,7 +215,9 @@ static void run_transcription(AVFilterContext *ctx, AVFrame *frame, int samples)
for (int i = 0; i < n_segments; ++i) {
const char *text = whisper_full_get_segment_text(wctx->ctx_wsp, i);
char *text_cleaned = av_strireplace(text + 1, "[BLANK_AUDIO]", "");
if (av_isspace(text[0]))
text++;
char *text_cleaned = av_strireplace(text, "[BLANK_AUDIO]", "");
if (av_strnlen(text_cleaned, 1) == 0) {
av_freep(&text_cleaned);