jianchang512 / stt

Voice Recognition to Text Tool / 一个离线运行的本地音视频转字幕工具,输出json、srt字幕、纯文字格式

Home Page:https://pyvideotrans.com

Repository from Github https://github.comjianchang512/sttRepository from Github https://github.comjianchang512/stt

Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory

Rockycocky opened this issue · comments

commented

下载的media模型 上传音频正常 转文字的时候报错

{'web_address': '10.10.61.117:9977', 'lang': 'zh', 'devtype': 'cuda', 'cuda_com_type': 'int8', 'beam_size': 1, 'best_of': 1, 'vad': True, 'temperature': 0, 'condition_on_previous_text': False, 'initial_prompt_zh': '以下是普通话内容,请转录为中文简体。'}

浏览器已打开,若未能自动打开,请手动打开网址 http://localhost:9977
res.status_code=200
d={'version': 'v0.0.92', 'version_num': 92}
以下是普通话内容,请转录为中文简体。
Could not load library libcudnn_ops_infer.so.8. Error: libcudnn_ops_infer.so.8: cannot open shared object file: No such file or directory
已放弃 (核心已转储)

pip install nvidia-cublas-cu11 nvidia-cudnn-cu11

SYSTRAN/faster-whisper#516

commented

sudo apt install libcudnn8 后解决了