配音阶段出错 [OmniVoice(本地内置)] CUDA out of memory. Tried to allocate 516.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Of the allocated memory 14.00 GiB is allocated by PyTorch, and 26.20 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
Traceback (most recent call last):
File "videotrans\task\job.py", line 35, in run
File "videotrans\task\job.py", line 154, in process_task
File "videotrans\task\_stage_dubbing.py", line 23, in dubbing
File "videotrans\task\_stage_dubbing.py", line 102, in _tts
File "videotrans\tts\__init__.py", line 207, in run
File "videotrans\tts\_base.py", line 93, in run
File "videotrans\tts\_omnivoice.py", line 119, in _exec
File "omnivoice\models\omnivoice.py", line 277, in from_pretrained
audio_tokenizer_path, device_map=tokenizer_device
File "G:\fanyi\_internal\transformers\modeling_utils.py", line 4137, in from_pretrained
loading_info, disk_offload_index = cls._load_pretrained_model(model, state_dict, checkpoint_files, load_config)
File "G:\fanyi\_internal\transformers\modeling_utils.py", line 4216, in _load_pretrained_model
caching_allocator_warmup(model, expanded_device_map, load_config.hf_quantizer)
File "G:\fanyi\_internal\transformers\modeling_utils.py", line 4810, in caching_allocator_warmup
_ = torch.empty(int(byte_count // 2), dtype=torch.float16, device=device, requires_grad=False)
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 516.00 MiB. GPU 0 has a total capacity of 8.00 GiB of which 0 bytes is free. Of the allocated memory 14.00 GiB is allocated by PyTorch, and 26.20 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
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:/sucai/暴发户/成片/25.mp4,
输出结果保存到文件夹: E:/sucai/暴发户/成片/_video_out/25-mp4,
临时文件夹: G:/fanyi/tmp/20288/06e6462f54
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-turbo, 发音语言: 简体中文, 断句方式:默认断句
翻译渠道:DeepSeek,原始语言:简体中文,目标语言:英语, 已选 发送完整字幕
配音渠道:OmniVoice(本地内置), 角色:clone, 配音语言:英语, 已选 二次语音识别
音量:+0%, 语速:+10%, 已选 音频加速, 未选 视频慢速
字幕: 嵌入软字幕
已选 分离人声与背景声, 已选 重新嵌入背景声, 背景音量0.8, 背景声音时长 短于 视频时长时: 拉长(降速播放),存在分离后的纯净人声文件,存在分离后的背景声音文件
代理地址:
=
system:Windows-10-10.0.18363-SP0
version:v4.05
frozen:True
language:zh
root_dir:G:/fanyi