chrissewell/whisperX
1
0
Fork 0
mirror of https://github.com/m-bain/whisperX.git synced 2025-07-01 18:17:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix short seg timestamps bug

Browse Source
This commit is contained in:
Max Bain
2023-01-28 19:04:19 +00:00
parent 50f3965fdb
commit 76f79f600a
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
whisperx/alignment.py
View File

@ -314,7 +314,7 @@ def align(
word_segments_arr[["segment-idx", "subsegment-idx", "word-idx"]] = per_word_grp["local-char-idx"].min().reset_index()[["segment-idx", "subsegment-idx", "word-idx"]].astype(int) word_segments_arr[["segment-idx", "subsegment-idx", "word-idx"]] = per_word_grp["local-char-idx"].min().reset_index()[["segment-idx", "subsegment-idx", "word-idx"]].astype(int)
segments_arr = {} segments_arr = {}
segments_arr["start"] = per_subseg_grp["start"].min().reset_index()["start"] segments_arr["start"] = per_subseg_grp["start"].min().reset_index()["start"]
segments_arr["end"] = per_subseg_grp["end"].min().reset_index()["end"] segments_arr["end"] = per_subseg_grp["end"].max().reset_index()["end"]
segments_arr = pd.DataFrame(segments_arr) segments_arr = pd.DataFrame(segments_arr)
segments_arr[["segment-idx", "subsegment-idx-start"]] = per_subseg_grp["start"].min().reset_index()[["segment-idx", "subsegment-idx"]] segments_arr[["segment-idx", "subsegment-idx-start"]] = per_subseg_grp["start"].min().reset_index()[["segment-idx", "subsegment-idx"]]
segments_arr["subsegment-idx-end"] = segments_arr["subsegment-idx-start"] + 1 segments_arr["subsegment-idx-end"] = segments_arr["subsegment-idx-start"] + 1