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
update readme
维石22d335cab897
diff --git a/README.md b/README.mdindex ddc26b2..28cfd8b 100644--- a/README.md+++ b/README.md@@ -105,6 +105,7 @@ python funclip/launch.py<img src="docs/images/guide.jpg"/>使用大语言模型裁剪请参考如下教程+<img src="docs/images/LLM_guide.png" width=360/>### B.通过命令行调用使用FunClip的相关功能diff --git a/README_en.md b/README_en.mdindex 206c464..cb5b1d0 100644--- a/README_en.md+++ b/README_en.md@@ -100,6 +100,7 @@ then visit ```localhost:7860``` you will get a Gradio service like below and you<img src="docs/images/guide.jpg"/>Follow the guide below to explore LLM based clipping:+<img src="docs/images/LLM_guide.png" width=360/>- Step1: Upload your video file (or try the example videos below)diff --git a/funclip/utils/trans_utils.py b/funclip/utils/trans_utils.pyindex f479f54..844fd62 100644--- a/funclip/utils/trans_utils.py+++ b/funclip/utils/trans_utils.py@@ -32,14 +32,12 @@ def proc(raw_text, timestamp, dest_text):offset = 0while True:fi = raw_text.find(dest_text, offset, len(raw_text))- # import pdb; pdb.set_trace()ti = raw_text[:fi].count(' ')if fi == -1:breakoffset = fi + ldmi.append(fi)ts.append([timestamp[ti][0]*16, timestamp[ti+ld-1][1]*16])- # import pdb; pdb.set_trace()return tsdef proc_spk(dest_spk, sd_sentences):@@ -48,7 +46,6 @@ def proc_spk(dest_spk, sd_sentences):d_start = d['timestamp'][0][0]d_end = d['timestamp'][-1][1]spkid=dest_spk[3:]- # import pdb; pdb.set_trace()if str(d['spk']) == spkid and d_end-d_start>999:ts.append([d['start']*16, d['end']*16])return tsdiff --git a/funclip/videoclipper.py b/funclip/videoclipper.pyindex f3444ff..5e379b4 100644--- a/funclip/videoclipper.py+++ b/funclip/videoclipper.py@@ -199,7 +199,7 @@ class VideoClipper():for _ts in ts: all_ts.append(_ts)else: # AI clip pass timestamp as input directlyall_ts = [[i[0]*16.0, i[1]*16.0] for i in timestamp_list]- import pdb; pdb.set_trace()+srt_index = 0time_acc_ost = 0.0ts = all_ts