#1448 ValueError: Requested int16 compute type, but the target device or backend do not support efficient int16 computation.

38.182* Posted at: 4 hours ago 👁6

Traceback (most recent call last):
File "videotrans\process\_overall.py", line 45, in run
File "faster_whisper\transcribe.py", line 675, in init
ValueError: Requested int16 compute type, but the target device or backend do not support efficient int16 computation.


=
system:Windows-10-10.0.26100-SP0
version:v3.84
frozen:True
language:zh
root_dir:D:/win-videotrans-v3.84

1 Replies

这个错误是由于您选择了 int16 作为 CUDA 数据类型,但您的硬件或 CUDA 环境不支持高效的 int16 计算。请按以下步骤解决:

  1. 在软件顶部菜单栏选择 工具/选项 -> 高级选项
  2. 找到 “faster/openai语音识别调整” 区域。
  3. “CUDA数据类型”int16 修改为 float16int8_float16
  4. 点击确定保存设置,然后重新运行任务。

float16 在大多数现代 NVIDIA 显卡上都能良好支持,并且能在保持较高精度的同时减少显存占用。如果问题依旧,请尝试 int8_float16 以进一步降低资源需求。

Post Your Reply
Open source and free maintenance is not easy. If this project is helpful to you, please consider making a small donation to help the project continue to maintain and update.

Donate: https://ko-fi.com/jianchang512

Trending Questions