-- Application started at 2026-07-19 14:50:31
1784443831:Loading resources...
1784443831:Loading main window...
1784443831:Initializing UI...
1784443831:SetupUI end...
1784443831:import recognition ...
1784443831:import tts ...
1784443831:import translate ...
1784443831:Get cache ...
1784443831:Set default value ...
1784443831:import voices list ...
1784443831:Set tts voice ...
[DEBUG] 上次缓存的角色:Yunxia(Male/CN),字幕嵌入类型:1,发音语言:英语,目标语言:简体中文,目标语言代码:zh-cn,模型:large-v3,TTS渠道[0]
1784443831:show main window ...
1784443831:Bind signal...
1784443831:set cursor...
1784443831:preload TTS win...
1784443831:preload STT win...
1784443831:preload translate srt win...
1784443831:end
[DEBUG] 返回缓存的编解码器 Windows-264: h264_nvenc
[DEBUG] 可用 Nvidia 显卡数: 1
[DEBUG] 找到 1 个 Nvidia GPUs, 耗时: 6s
[DEBUG] 返回缓存的编解码器 Windows-265: hevc_nvenc
[DEBUG] start 9 jobs
[DEBUG] app_cfg.proxy='http://127.0.0.1:7897'
[DEBUG] 无法连接 huggingface.co, 使用镜像替换: hf-mirror.com
[DEBUG] 批量翻译模式,每批次 1
[DEBUG] 进入第 0 批次,当前批次数量:1
[DEBUG] [TransCreate]最终配置信息:self=TransCreate(uuid='4ec31c0163', proxy_str='http://127.0.0.1:7897', last_down_time=0, precent=1, hasend=False, should_recogn=True, should_trans=True, should_dubbing=True, should_separate=False, should_hebing=True, source_srt_list=[], target_srt_list=[], video_time=0.0, is_copy_video=False, video_codec_num=264, ignore_align=False, is_audio_trans=False, clone_ref='', cost_duration=1784443845.746128, should_recogn2=True)
self.cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频 批量翻译模式 每批1个
原始输入文件名: E:/BaiduNetdisk
/The AI Engineer Course 2025 Complete AI Engineer Bootcamp/5 - Intro to AI Module Understanding Generative AI/26 - The importance of foundation models.mp4,
输出结果保存到文件夹: E:/BaiduNetdisk
/AI视频教程/26 - The importance of foundation models-mp4,
临时文件夹: D:/APP/tools/pyvideotrans/tmp/19708/4ec31c0163
已选 清理已存在
已选 启用CUDA加速
未选 降噪
已选 识别说话人,最大说话人数量不限制
语音识别:faster-whisper(本地内置), model_name: large-v3, 发音语言: 英语, 断句方式:默认断句
翻译渠道:DeepSeek,原始语言:英语,目标语言:简体中文, 已选 发送完整字幕
配音渠道:Edge-TTS(免费), 角色:Yunxia(Male/CN), 配音语言:简体中文, 已选 二次语音识别
音量:+0%, 语速:+0%, 已选 音频加速, 未选 视频慢速
字幕: 嵌入硬字幕
已选 仅输出mp4
代理地址:
http://127.0.0.1:7897[DEBUG] The file info after process:result={'video_fps': 30.0, 'r_frame_rate': 30.0, 'video_codec_name': 'h264', 'audio_codec_name': 'aac', 'width': 1920, 'height': 1080, 'time': 169866, 'streams_len': 2, 'streams_audio': 1, 'video_streams': 1, 'color': 'yuv420p'}
[DEBUG] 从 modelscope.cn 下载模型 model_id='large-v3'
2026-07-19 14:51:08,003 - modelscope - WARNING - We can not confirm the cached file is for revision: master
[DEBUG] [新进程任务 开始:title='STT use large-v3']
[DEBUG] 新进程任务 参数:kwargs={'detect_language': 'en', 'model_name': 'large-v3', 'logs_file': 'D:/APP/tools/pyvideotrans/tmp/19708/4ec31c0163/faster-en-1784443868.0033581.log', 'is_cuda': True, 'no_speech_threshold': 0.6, 'condition_on_previous_text': False, 'speech_timestamps': None, 'audio_file': 'D:/APP/tools/pyvideotrans/tmp/19708/4ec31c0163/en.wav', 'local_dir': 'D:/APP/tools/pyvideotrans/models/models--Systran--faster-whisper-large-v3', 'compute_type': 'default', 'jianfan': False, 'audio_duration': 170027, 'hotwords': '', 'prompt': '', 'beam_size': 1, 'best_of': 1, 'temperature': '', 'repetition_penalty': 1.0, 'compression_ratio_threshold': 2.4, 'max_speech_ms': 5000, 'subtitle_srt': 'D:/APP/tools/pyvideotrans/tmp/faster-20260719-14_51_08.srt', 'device_index': 0}
[DEBUG] GPU进程池:max_workers=1
[DEBUG] 开始加载 faster-whisper模型large-v3,数据类型:default
[DEBUG] [faster_whisper]加载模型large-v3: is_cuda=True,_compute_type='default'
[DEBUG] 直接传递完整音频,由faster-whisper内部VAD处理,返回字级时间戳数据
[DEBUG] faster-whisper模式下,对large-v3模型返回的字级时间戳进行断句
[DEBUG] 断句完毕返回结果
[DEBUG] faster-whisper下已临时保存识别结果到 D:/APP/tools/pyvideotrans/tmp/faster-20260719-14_51_08.srt,防止进程崩溃后永久等待
[DEBUG] [新进程任务 title='STT use large-v3'] 已返回
[DEBUG] [新进程任务 结束:title='STT use large-v3'],耗时27.27536702156067s
[DEBUG] 移除无效字幕行
[DEBUG] 修正重叠时间轴
[DEBUG] 开始移除每条字幕末尾标点
[DEBUG] [新进程任务 开始:title='Begin separating the speakers:built']
[DEBUG] 新进程任务 参数:kwargs={'input_file': 'D:/APP/tools/pyvideotrans/tmp/19708/4ec31c0163/en.wav', 'subtitles_file': 'D:/APP/tools/pyvideotrans/tmp/19708/4ec31c0163/diariz-1784443895.2832563.json', 'speak_file': 'D:/APP/tools/pyvideotrans/tmp/19708/4ec31c0163/speaker.json', 'num_speakers': -1, 'language': 'en'}
[DEBUG] CPU进程池:max_workers=8
[DEBUG] 开始说话人分离,使用内置模型 language='en',num_speakers=-1
版本V4.06