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
1.修复了在音频模式下的报错问题(launch.py line 24,少传了一个参数导致state接收到的参数实际为hotwords的值) 2.修复了日志format问题(videoclipper.py line 41)
xlchen546a7eb55b05
diff --git a/funclip/launch.py b/funclip/launch.pyindex 0473770..b163ed1 100644--- a/funclip/launch.py+++ b/funclip/launch.py@@ -21,7 +21,7 @@ if __name__ == "__main__":theme = gr.Theme.load("funclip/utils/theme.json")def audio_recog(audio_input, sd_switch, hotwords, output_dir):- return audio_clipper.recog(audio_input, sd_switch, hotwords, output_dir=output_dir)+ return audio_clipper.recog(audio_input, sd_switch, None, hotwords, output_dir=output_dir)def video_recog(video_input, sd_switch, hotwords, output_dir):return audio_clipper.video_recog(video_input, sd_switch, hotwords, output_dir=output_dir)diff --git a/funclip/videoclipper.py b/funclip/videoclipper.pyindex c12816c..ae66d5e 100644--- a/funclip/videoclipper.py+++ b/funclip/videoclipper.py@@ -38,7 +38,7 @@ class VideoClipper():if sr != 16000: # resample with librosadata = librosa.resample(data, orig_sr=sr, target_sr=16000)if len(data.shape) == 2: # multi-channel wav input- logging.warning("Input wav shape: {}, only first channel reserved.").format(data.shape)+ logging.warning("Input wav shape: {}, only first channel reserved.".format(data.shape))data = data[:,0]state['audio_input'] = (sr, data)if sd_switch == 'Yes':