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 Unequal Stack Size VAD error

Browse Source
This commit is contained in:
Max Bain
2023-05-26 20:36:03 +01:00
parent 9ffb7e7a23
commit 42b4909bc0
2 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
whisperx/alignment.py
View File

@ -298,6 +298,8 @@ def align(
aligned_subsegments["end"] = interpolate_nans(aligned_subsegments["end"], method=interpolate_method)
# concatenate sentences with same timestamps
agg_dict = {"text": " ".join, "words": "sum"}
if model_lang in LANGUAGES_WITHOUT_SPACES:
agg_dict["text"] = "".join
if return_char_alignments:
agg_dict["chars"] = "sum"
aligned_subsegments= aligned_subsegments.groupby(["start", "end"], as_index=False).agg(agg_dict)

10
whisperx/vad.py
View File

@ -147,8 +147,6 @@ class Binarize:
if is_active:
curr_duration = t - start
if curr_duration > self.max_duration:
# if curr_duration > 15:
# import pdb; pdb.set_trace()
search_after = len(curr_scores) // 2
# divide segment
min_score_div_idx = search_after + np.argmin(curr_scores[search_after:])
@ -159,21 +157,21 @@ class Binarize:
curr_scores = curr_scores[min_score_div_idx+1:]
curr_timestamps = curr_timestamps[min_score_div_idx+1:]
# switching from active to inactive
elif y < self.offset:
elif y <= self.offset:
region = Segment(start - self.pad_onset, t + self.pad_offset)
active[region, k] = label
start = t
is_active = False
curr_scores = []
curr_timestamps = []
curr_scores.append(y)
curr_timestamps.append(t)
# currently inactive
else:
# switching from inactive to active
if y > self.onset:
if y >= self.onset:
start = t
is_active = True
curr_scores.append(y)
curr_timestamps.append(t)
# if active at the end, add final region
if is_active: