网络连接失败
=
system:Windows-10-10.0.19045-SP0
version:v3.98
frozen:True
language:zh
root_dir:D:/pyvideotrans
[DEBUG] [Calc] Mode=Both Line=1 | Source=8200 Dubb=13007 -> TargetV=10603 TargetA=10603
[DEBUG] [Audio] 开始处理 1 个音频变速任务
[DEBUG] CPU进程池:max_workers=5
[DEBUG] [Audio-RB] D:/pyvideotrans/tmp/1948/c0ffd42274/dubb-0.wav 原长:13007ms -> 目标:10603ms 倍率:1.23
[DEBUG] [Video] 提交 1 个视频处理任务
[DEBUG] [Video-Cut] 片段0 [原:0-8200ms] [目标:10603ms] [PTS:1.2930] 准备开始处理...
[DEBUG] [Video-Cut] 片段0 [原:0-8200ms] [目标:10603ms] [PTS:1.2930] 完成。实际生成时长: 10559ms
[DEBUG] [Video-Concat] 合并 1 个片段 -> D:/pyvideotrans/tmp/1948/c0ffd42274/merged_video.mp4
[DEBUG] [SpeedRate] 新视频生成完毕，总时长: 10603ms
[DEBUG] [Audio] 开始对齐拼接...
[DEBUG] [Audio-Sync] Line=1 | 音频溢出截断 10603->10559 | [current_slot_audio_len=10603 slot_duration=10559] | Timeline: 0 -> 10559
[DEBUG] concat_txt='D:/pyvideotrans/tmp/1948/c0ffd42274/final_audio_concat.txt',filelist[0]='D:/pyvideotrans/tmp/1948/c0ffd42274/final_slot_cut_0.wav'
[DEBUG] [Audio-Concat] 最终音频已生成: D:/pyvideotrans/tmp/1948/c0ffd42274/target.wav
[DEBUG] 进入二次识别
[DEBUG] [recognition]__init__:kwargs={'detect_language': 'en', 'audio_file': 'D:/pyvideotrans/tmp/1948/c0ffd42274/recogn2pass-1773969138.701508.wav', 'cache_folder': 'D:/pyvideotrans/tmp/1948/c0ffd42274', 'model_name': 'large-v3-turbo', 'uuid': 'c0ffd42274', 'is_cuda': True, 'subtitle_type': 0, 'recogn_type': 7, 'max_speakers': -1, 'llm_post': False, 'recogn2pass': True}
[DEBUG] BaseRecogn 初始化
[DEBUG] Before VAD tenvad,_min_speech=1500ms,_max_speech=3000ms,_min_silence=70ms
[DEBUG] [Ten-VAD]Fix after:VAD断句参数：threshold=0.4,min_speech_duration_ms=1500ms,max_speech_duration_ms=3000ms,min_silent_duration_ms=70ms
[DEBUG] [Ten-VAD]音频能量: 4455.939660479212, 调整后阈值: 0.4