#7060 [enforce fail at alloc_cpu.cpp:116] data. DefaultCPUAllocator: not enough memory: you tried to allocate 13200199680 byte

[enforce fail at alloc_cpu.cpp:116] data. DefaultCPUAllocator: not enough memory: you tried to allocate 13200199680 bytes.:Traceback (most recent call last):
File "videotrans\process\stt_qwen.py", line 56, in qwen3asr_fun
File "D:\AI\pyvideotrans\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "qwen_asr\inference\qwen3_asr.py", line 383, in transcribe

raw_outputs = self._infer_asr(chunk_ctx, chunk_wavs, chunk_lang)

File "qwen_asr\inference\qwen3_asr.py", line 485, in _infer_asr

return self._infer_asr_transformers(contexts, wavs, languages)

File "qwen_asr\inference\qwen3_asr.py", line 510, in _infer_asr_transformers

text_ids = self.model.generate(**inputs, max_new_tokens=self.max_new_tokens)

File "D:\AI\pyvideotrans\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "qwen_asr\core\transformers_backend\modeling_qwen3_asr.py", line 1353,
......
=True, **thinker_kwargs)
File "D:\AI\pyvideotrans\_internal\torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "D:\AI\pyvideotrans\_internal\transformers4576\generation\utils.py", line 2566, in generate

result = decoding_method(

File "D:\AI\pyvideotrans\_internal\transformers4576\generation\utils.py", line 2786, in _sample

outputs = self(**model_inputs, return_dict=True)

File "D:\AI\pyvideotrans\_internal\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

File "D:\AI\pyvideotrans\_internal\torch\nn\modules\module.py", line 1762, in _call_impl

return forward_call(*args, **kwargs)

File "D:\AI\pyvideotrans\_internal\transformers4576\utils\generic.py", line 918, in wrapper

output = func(self, *args, **kwargs)

File "qwen_asr\core\transformers_backend\modeling_qwen3_asr.py", line 1241, in forward

logits = self.lm_head(hidden_states)

File "D:\AI\pyvideotrans\_internal\torch\nn\modules\module.py", line 1751, in _wrapped_call_impl

return self._call_impl(*args, **kwargs)

File "D:\AI\pyvideotrans\_internal\torch\nn\modules\module.py", line 1762, in _call_impl

return forward_call(*args, **kwargs)

File "D:\AI\pyvideotrans\_internal\torch\nn\modules\linear.py", line 125, in forward

return F.linear(input, self.weight, self.bias)

RuntimeError: [enforce fail at alloc_cpu.cpp:116] data. DefaultCPUAllocator: not enough memory: you tried to allocate 13200199680 bytes.

cfg=[TaskCfgVTT]当前工作模式: 翻译视频或音频 单视频模式
原始输入文件名: G:/viedo/sex/福冈/FC2PPV 4786921.mp4,
输出结果保存到文件夹: G:/viedo/sex/福冈/_video_out/FC2PPV 4786921-mp4,
临时文件夹: D:/AI/pyvideotrans/tmp/18948/18a97f3a2b
已选 清理已存在
未启用CUDA加速
未选 降噪
语音识别:Qwen-ASR(内置), 1.7B, 发音语言: 日语, 断句方式:默认断句
翻译渠道:兼容AI/本地模型,原始语言:日语,目标语言:简体中文, 已选 发送完整字幕
未选 配音角色，不进行配音
字幕: 嵌入硬字幕