[DEBUG] 开始语音识别:渠道0
[DEBUG] [新进程任务 开始:STT use large-v3]
[DEBUG] 任务参数:kwargs={'detect_language': 'en', 'model_name': 'large-v3', 'logs_file': 'D:/pyvideotrans/tmp/6160/2b16658002/faster-en-1787801438.7721088.log', 'is_cuda': True, 'no_speech_threshold': 0.6, 'condition_on_previous_text': False, 'speech_timestamps': None, 'audio_file': 'D:/pyvideotrans/tmp/6160/2b16658002/en.wav', 'local_dir': 'D:/pyvideotrans/models/models--Systran--faster-whisper-large-v3', 'compute_type': 'default', 'jianfan': False, 'audio_duration': 8153003, 'hotwords': None, 'prompt': '', 'beam_size': 5, 'best_of': 5, 'temperature': '', 'repetition_penalty': 1.0, 'compression_ratio_threshold': 2.4, 'max_speech_ms': 5000, 'device_index': 0}
[DEBUG] GPU进程池:max_workers=1
[DEBUG] [faster_whisper]加载模型:当前 is_cuda=True,_compute_type='default'
[DEBUG] faster-whisper模式下,对large-v3模型返回的断句结果重新修正
[DEBUG] 断句结果重新修正完毕
[DEBUG] 返回识别结果
[DEBUG] [新进程任务 结束:STT use large-v3],耗时1282.513066053
......
lf.ainame='deepseek',self.model_name='deepseek-v4-pro',self.api_url='https://api.deepseek.com/v1/',self.reasoning_effort=None]
[INFO] Starting call to 'videotrans.translator._openaicompat.OpenAICampat._item_task', this is the 1st time calling it.
[DEBUG] 字幕翻译:[self.ainame='deepseek',self.model_name='deepseek-v4-pro',self.api_url='https://api.deepseek.com/v1/',self.reasoning_effort=None]
[INFO] Starting call to 'videotrans.translator._openaicompat.OpenAICampat._item_task', this is the 1st time calling it.
[DEBUG] 字幕翻译:[self.ainame='deepseek',self.model_name='deepseek-v4-pro',self.api_url='https://api.deepseek.com/v1/',self.reasoning_effort=None]
[INFO] Starting call to 'videotrans.translator._openaicompat.OpenAICampat._item_task', this is the 1st time calling it.
[DEBUG] 字幕翻译:[self.ainame='deepseek',self.model_name='deepseek-v4-pro',self.api_url='https://api.deepseek.com/v1/',self.reasoning_effort=None]
[INFO] Starting call to 'videotrans.translator._openaicompat.OpenAICampat._item_task', this is the 1st time calling it.
[DEBUG] 字幕翻译:[self.ainame='deepseek',self.model_name='deepseek-v4-pro',self.api_url='https://api.deepseek.com/v1/',self.reasoning_effort=None]
[INFO] Starting call to 'videotrans.translator._openaicompat.OpenAICampat._item_task', this is the 1st time calling it.
[DEBUG] 字幕翻译:[self.ainame='deepseek',self.model_name='deepseek-v4-pro',self.api_url='https://api.deepseek.com/v1/',self.reasoning_effort=None]
[DEBUG] 以SRT格式翻译,原始字幕行数:2883,翻译后行数:2883
[DEBUG] 原始语言字幕和目标语言字幕行数一致,均为 source_len=2883
[DEBUG] 跳过二次识别
[DEBUG]
==准备要嵌入的字幕:self.cfg.subtitle_type=1
=
[DEBUG] 最终确定字幕嵌入类型:1 ,目标字幕语言:zho, 字幕文件:D:/pyvideotrans/tmp/6160/2b16658002/end.srt
[DEBUG] [set_ass_font] 未修改硬字幕样式,跳过样式替换
[DEBUG] [FFMPEG-CMD]:
ffmpeg -hide_banner -nostdin -ignore_unknown -threads 0 -y -i novoice.mp4 -vf tpad=stop_mode=clone:stop_duration=1.094 -c:v libx264 -crf 23 -preset medium -an final_video_with_freeze_lastend.mp4