diff options
| author | Zhao Zhili <zhilizhao@tencent.com> | 2025-08-15 20:39:49 +0800 |
|---|---|---|
| committer | michaelni <michael@niedermayer.cc> | 2025-08-16 13:58:14 +0000 |
| commit | 1d06e8ddcd8c14232d0a3c2b1c21e50b232549b4 (patch) | |
| tree | 04e8187ac79ab209ff82daf8ebc567fda86cd3d0 | |
| parent | 30e695692041888d727159c6279f433540453c3f (diff) | |
| download | ffmpeg-1d06e8ddcd8c14232d0a3c2b1c21e50b232549b4.tar.gz | |
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.
| -rw-r--r-- | libavfilter/af_whisper.c | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/libavfilter/af_whisper.c b/libavfilter/af_whisper.c index 186b624504..bd145d6d1d 100644 --- a/libavfilter/af_whisper.c +++ b/libavfilter/af_whisper.c @@ -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); |