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

v2 lets goo

Browse Source
This commit is contained in:
Max Bain
2023-04-01 00:10:45 +01:00
parent bc2776017e
commit 189aeac83e
2 changed files with 2 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
whisperx/alignment.py
View File

@ -372,10 +372,7 @@ def align(
for sdx, srow in segments_arr.iterrows(): for sdx, srow in segments_arr.iterrows():
seg_idx = int(srow["segment-idx"]) seg_idx = int(srow["segment-idx"])
try:
sub_start = int(srow["subsegment-idx-start"]) sub_start = int(srow["subsegment-idx-start"])
except:
import pdb; pdb.set_trace()
sub_end = int(srow["subsegment-idx-end"]) sub_end = int(srow["subsegment-idx-end"])
seg = transcript[seg_idx] seg = transcript[seg_idx]

14
whisperx/vad.py
View File

@ -302,17 +302,3 @@ def merge_chunks(segments, chunk_size):
"segments": seg_idxs, "segments": seg_idxs,
}) })
return merged_segments return merged_segments
if __name__ == "__main__":
import pandas as pd
input_fp = "tt298650_sync.wav"
df = pd.read_csv(f"/work/maxbain/tmp/{input_fp}.sad", sep=" ", header=None)
print(len(df))
N = 0.15
g = df[0].sub(df[1].shift())
input_base = input_fp.split('.')[0]
df = df.groupby(g.gt(N).cumsum()).agg({0:'min', 1:'max'})
df.to_csv(f"/work/maxbain/tmp/{input_base}.lab", header=None, index=False, sep=" ")
print(df)
import pdb; pdb.set_trace()