#5216 TaskCfgSTT(uuid='2d65212b45', name='E:/DownLoad/DCL/ASHLEY MASON – MOMMY PANTY ANAL.mp4', dirname='E:/DownLoad/DCL', noe

106.61* Posted at: 2 hours ago

语音识别阶段出错[openai-whisper(本地)] Expected parameter logits (Tensor of shape (1, 51866)) of distribution Categorical(logits: torch.Size([1, 51866])) to satisfy the constraint IndependentConstraint(Real(), 1), but found invalid values:
tensor([[nan, nan, nan, ..., nan, nan, nan]], device='cuda:0'):Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 102, in openai_whisper
File "whisper\transcribe.py", line 295, in transcribe
File "whisper\transcribe.py", line 201, in decode_with_fallback
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "whisper\decoding.py", line 824, in decode
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "whisper\decoding.py", line 737, in run
File "whisper\decoding.py", line 703, in _main_loop
File "whisper\decoding.py", line 283, in update
File "torch\distributions\categorical.py", line 73, in init

super().__init__(batch_shape, validate_args=validate_args)

File "torch\distributions\distribution.py", line 72, in init

raise ValueError(

ValueError: Expected parameter logits (Tensor of shape (1, 51866)) of distribution Categorical(logits: torch.Size([1, 51866])) to satisfy the constraint IndependentConstraint(Real(), 1), but found invalid values:
tensor([[nan, nan, nan, ..., nan, nan, nan]], device='cuda:0')

Traceback (most recent call last):

File "videotrans\task\job.py", line 35, in run

File "videotrans\task\job.py", line 100, in process_task

File "videotrans\task\speech2text.py", line 126, in recogn

File "videotrans\recognition\__init__.py", line 190, in run

File "videotrans\recognition\_base.py", line 94, in run

File "videotrans\recognition\_whisper.py", line 34, in _exec

File "videotrans\recognition\_whisper.py", line 77, in _openai

File "videotrans\configure\base.py", line 253, in _new_process

videotrans.configure.excepts.VideoTransError: Expected parameter logits (Tensor of shape (1, 51866)) of distribution Categorical(logits: torch.Size([1, 51866])) to satisfy the constraint IndependentConstraint(Real(), 1), but found invalid values:
tensor([[nan, nan, nan, ..., nan, nan, nan]], device='cuda:0'):Traceback (most recent call last):
File "videotrans\process\stt_fun.py", line 102, in openai_whisper
File "whisper\transcribe.py", line 295, in transcribe
File "whisper\transcribe.py", line 201, in decode_with_fallback
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "whisper\decoding.py", line 824, in decode
File "torch\utils\_contextlib.py", line 116, in decorate_context

return func(*args, **kwargs)

File "whisper\decoding.py", line 737, in run
File "whisper\decoding.py", line 703, in _main_loop
File "whisper\decoding.py", line 283, in update
File "torch\distributions\categorical.py", line 73, in init

super().__init__(batch_shape, validate_args=validate_args)

File "torch\distributions\distribution.py", line 72, in init

raise ValueError(

ValueError: Expected parameter logits (Tensor of shape (1, 51866)) of distribution Categorical(logits: torch.Size([1, 51866])) to satisfy the constraint IndependentConstraint(Real(), 1), but found invalid values:
tensor([[nan, nan, nan, ..., nan, nan, nan]], device='cuda:0')
TaskCfgSTT(uuid='2d65212b45', name='E:/DownLoad/DCL/ASHLEY MASON – MOMMY PANTY ANAL.mp4', dirname='E:/DownLoad/DCL', noextname='ASHLEY MASON – MOMMY PANTY ANAL', basename='ASHLEY MASON – MOMMY PANTY ANAL.mp4', ext='mp4', target_dir='D:/win-pyvideotrans-v4.01-0602/output/recogn', cache_folder='D:/win-pyvideotrans-v4.01-0602/tmp/11692/2d65212b45', is_cuda=True, source_language=None, source_language_code=None, source_sub=None, source_wav=None, source_wav_output=None, target_language=None, target_language_code=None, target_sub='D:/win-pyvideotrans-v4.01-0602/output/recogn/ASHLEY MASON – MOMMY PANTY ANAL.srt', target_wav=None, target_wav_output=None, detect_language='auto', recogn_type=1, model_name='large-v3-turbo', shibie_audio='D:/win-pyvideotrans-v4.01-0602/tmp/11692/2d65212b45/ASHLEY MASON – MOMMY PANTY ANAL-1781529599.2402139.wav', remove_noise=False, enable_diariz=False, nums_diariz=0, rephrase=0, fix_punc=False)


=
system:Windows-10-10.0.26100-SP0
version:v4.01
frozen:True
language:zh
root_dir:D:/win-pyvideotrans-v4.01-0602

1 Replies

该错误是由于 Whisper 模型在 GPU 上推理时出现数值不稳定(NaN),常见于显存不足、模型文件损坏或 CUDA 环境不兼容。

  1. 检查 CUDA 环境:确认显卡驱动已更新至最新,且已安装 CUDA 12.8+ 和 cuDNN 9.11+。若未正确配置,请参考官方 GPU 配置教程。
  2. 降低模型大小:当前使用的 large-v3-turbo 模型对显存要求较高,建议尝试切换为 smallbase 模型(在语音识别渠道下拉菜单中更换)。
  3. 调低识别精度参数:进入 菜单 -> 工具 -> 高级选项 -> 语音识别参数,将 beam_sizebest_of 设为 1,并关闭 启用上下文感知,以降低运算压力。
  4. 测试 CPU 模式:取消勾选“CUDA加速”,使用 CPU 运行一次,观察是否还会报错。若 CPU 正常,则问题出在 GPU 环境或显存不足。
  5. 重新下载模型:若文件损坏,可删除 models/ 下对应模型文件夹(如 models--openai--whisper-large-v3-turbo),重启软件后会自动重新下载。

如果仍无法解决,请提供 logs/ 目录下最新的日志文件(后约30行)以便进一步分析。

请查阅相关文档:

Post Your Reply