Skip to content

FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.

bug fix

shixian.shiba348b0fc197
diff --git a/ClipVideo/clipvideo/subtitle_utils.py b/ClipVideo/clipvideo/subtitle_utils.py
index a3d9a47..797a0dd 100644
--- a/ClipVideo/clipvideo/subtitle_utils.py
+++ b/ClipVideo/clipvideo/subtitle_utils.py
@@ -34,10 +34,13 @@ class Text2SRT():
return res
def len(self):
return len(self.token_list)
- def srt(self):
- return "{} --> {}\n{}\n".format(self.start_time, self.end_time, self.text())
- def time(self):
- return (self.start_sec/1000, self.end_sec/1000)
+ def srt(self, acc_ost=0.0):
+ return "{} --> {}\n{}\n".format(
+ time_convert(self.start_sec+acc_ost*1000),
+ time_convert(self.end_sec+acc_ost*1000),
+ self.text())
+ def time(self, acc_ost=0.0):
+ return (self.start_sec/1000+acc_ost, self.end_sec/1000+acc_ost)
def generate_srt(sentence_list):
@@ -47,7 +50,7 @@ def generate_srt(sentence_list):
srt_total += "{}\n{}".format(i, t2s.srt())
return srt_total
-def generate_srt_clip(sentence_list, start, end, begin_index=0):
+def generate_srt_clip(sentence_list, start, end, begin_index=0, time_acc_ost=0.0):
start, end = int(start * 1000), int(end * 1000)
srt_total = ''
cc = 1 + begin_index
@@ -58,10 +61,10 @@ def generate_srt_clip(sentence_list, start, end, begin_index=0):
if d['ts_list'][0][0] >= end:
break
# parts in between
- if (d['ts_list'][-1][1] < end and d['ts_list'][0][0] > start) or (d['ts_list'][-1][1] == end and d['ts_list'][0][0] == start):
+ if (d['ts_list'][-1][1] <= end and d['ts_list'][0][0] > start) or (d['ts_list'][-1][1] == end and d['ts_list'][0][0] == start):
t2s = Text2SRT(d['text_seg'], d['ts_list'], offset=start)
- srt_total += "{}\n{}".format(cc, t2s.srt())
- subs.append((t2s.time(), t2s.text()))
+ srt_total += "{}\n{}".format(cc, t2s.srt(time_acc_ost))
+ subs.append((t2s.time(time_acc_ost), t2s.text()))
cc += 1
continue
if d['ts_list'][0][0] <= start:
@@ -84,8 +87,8 @@ def generate_srt_clip(sentence_list, start, end, begin_index=0):
_ts = d['ts_list'][_start:_end]
if len(ts):
t2s = Text2SRT(_text, _ts, offset=start)
- srt_total += "{}\n{}".format(cc, t2s.srt())
- subs.append((t2s.time(), t2s.text()))
+ srt_total += "{}\n{}".format(cc, t2s.srt(time_acc_ost))
+ subs.append((t2s.time(time_acc_ost), t2s.text()))
cc += 1
continue
if d['ts_list'][-1][1] > end:
@@ -96,9 +99,9 @@ def generate_srt_clip(sentence_list, start, end, begin_index=0):
_ts = d['ts_list'][:j]
if len(_ts):
t2s = Text2SRT(_text, _ts, offset=start)
- srt_total += "{}\n{}".format(cc, t2s.srt())
+ srt_total += "{}\n{}".format(cc, t2s.srt(time_acc_ost))
subs.append(
- (t2s.time(), t2s.text())
+ (t2s.time(time_acc_ost), t2s.text())
)
cc += 1
continue
diff --git a/ClipVideo/clipvideo/videoclipper.py b/ClipVideo/clipvideo/videoclipper.py
index 491bc45..6d50f9d 100644
--- a/ClipVideo/clipvideo/videoclipper.py
+++ b/ClipVideo/clipvideo/videoclipper.py
@@ -105,36 +105,40 @@ class VideoClipper():
all_ts = []
srt_index = 0
+ time_acc_ost = 0.0
for _dest_text in dest_text.split('#'):
_dest_text = pre_proc(_dest_text)
ts = proc(recog_res_raw, timestamp, _dest_text)
for _ts in ts: all_ts.append(_ts)
+ import pdb; pdb.set_trace()
ts = all_ts
clip_srt = ""
if len(ts):
start, end = ts[0][0] / 16000, ts[0][1] / 16000
+ srt_clip, subs, srt_index = generate_srt_clip(sentences, start, end, begin_index=srt_index, time_acc_ost=time_acc_ost)
start, end = start+start_ost/1000.0, end+end_ost/1000.0
video_clip = video.subclip(start, end)
start_end_info = "from {} to {}".format(start, end)
- srt_clip, subs, srt_index = generate_srt_clip(sentences, start, end, begin_index=srt_index)
clip_srt += srt_clip
if add_sub:
generator = lambda txt: TextClip(txt, font='./font/STHeitiMedium.ttc', fontsize=font_size, color=font_color)
subtitles = SubtitlesClip(subs, generator)
video_clip = CompositeVideoClip([video_clip, subtitles.set_pos(('center','bottom'))])
concate_clip = [video_clip]
+ time_acc_ost += end+end_ost/1000.0 - (start+start_ost/1000.0)
for _ts in ts[1:]:
start, end = _ts[0] / 16000, _ts[1] / 16000
+ srt_clip, subs, srt_index = generate_srt_clip(sentences, start, end, begin_index=srt_index-1, time_acc_ost=time_acc_ost)
start, end = start+start_ost/1000.0, end+end_ost/1000.0
_video_clip = video.subclip(start, end)
start_end_info += ", from {} to {}".format(start, end)
- srt_clip, subs, srt_index = generate_srt_clip(sentences, start, end, begin_index=srt_index-1)
clip_srt += srt_clip
if add_sub:
generator = lambda txt: TextClip(txt, font='./font/STHeitiMedium.ttc', fontsize=font_size, color=font_color)
subtitles = SubtitlesClip(subs, generator)
_video_clip = CompositeVideoClip([_video_clip, subtitles.set_pos(('center','bottom'))])
concate_clip.append(copy.copy(_video_clip))
+ time_acc_ost += end+end_ost/1000.0 - (start+start_ost/1000.0)
message = "{} periods found in the audio: ".format(len(ts)) + start_end_info
logging.warning("Concating...")
if len(concate_clip) > 1: