FunASR-powered video transcription, subtitle generation, and LLM-assisted clipping tool with a local Gradio UI.
Python ai-toolsai-video-editingasrauto-subtitleschinesecontent-creationfunasrfunclipgradiollmparaformerspeech-recognitionspeech-to-textsubtitles-generatortranscriptionvideo-editingvideo-processingvideo-subtitlesvideo-transcriptionwhisper-alternative
Merge branch 'speaker-diarization' into main
Hui Wang852d4f02e848
diff --cc ClipVideo/clipvideo/subtitle_utils.pyindex d1f7f7b,797a0dd..705f13e--- a/ClipVideo/clipvideo/subtitle_utils.py+++ b/ClipVideo/clipvideo/subtitle_utils.py@@@ -34,42 -34,23 +34,45 @@@ class Text2SRT()return resdef 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 distribute_spk(sentence_list, sd_time_list):+ sd_sentence_list = []+ for d in sentence_list:+ sentence_start = d['ts_list'][0][0]+ sentence_end = d['ts_list'][-1][1]+ sentence_spk = 0+ max_overlap = 0+ for sd_time in sd_time_list:+ spk_st, spk_ed, spk = sd_time+ spk_st = spk_st*1000+ spk_ed = spk_ed*1000+ overlap = max(+ min(sentence_end, spk_ed) - max(sentence_start, spk_st), 0)+ if overlap > max_overlap:+ max_overlap = overlap+ sentence_spk = spk+ d['spk'] = sentence_spk+ sd_sentence_list.append(d)+ return sd_sentence_listdef generate_srt(sentence_list):srt_total = ''for i, d in enumerate(sentence_list):t2s = Text2SRT(d['text_seg'], d['ts_list'])- srt_total += "{}\n{}".format(i, t2s.srt())+ if 'spk' in d:+ srt_total += "{} spk{}\n{}".format(i, d['spk'], t2s.srt())+ else:+ 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_indexdiff --cc ClipVideo/clipvideo/videoclipper.pyindex 41fe9cf,0b54957..a649076--- a/ClipVideo/clipvideo/videoclipper.py+++ b/ClipVideo/clipvideo/videoclipper.py@@@ -119,17 -105,12 +119,18 @@@ class VideoClipper()all_ts = []srt_index = 0+ if dest_spk is None or dest_spk == '' or 'sd_sentences' not in state:+ 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)+ else:+ for _dest_spk in dest_spk.split('#'):+ ts = proc_spk(_dest_spk, state['sd_sentences'])+ for _ts in ts: all_ts.append(_ts)+ 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)ts = all_ts+ ts.sort()clip_srt = ""if len(ts):start, end = ts[0][0] / 16000, ts[0][1] / 16000