dream Catcher

在 predictor = paddle_infer.create_predictor(config) 前面加上代码 ``` config.switch_ir_optim(False) config.enable_use_gpu(100, 0) ```

使用这种方式可以解决你的问题 ``` jieba.posseg.initialize("user_dict.txt") # 手动初始化（可选） sentence = '理想西溪金座在哪个位置。 for pair in jieba.posseg.cut(sentence): print(pair) ```

Thank you for your help. I know ASR is an autoregressive model。After testing, it looks like a cumulative score. How can I calculate the score for each token  For...

> If you can structure code within train and predict and data load parts, or use more classes, make it easy to use and modify. > > I have create...

I tried, but failed, only building a CPU image, the command is： > python3 build.py --enable-logging --endpoint http --endpoint grpc --backend python I built it in the latest main branch...

Just to add, my data volume is about 50000 entries, and the data table contains several indexes. When executing delete from table, it takes about 15 seconds. During these 15...

I encountered the same problem, only building a CPU image, the command is： > **` python3 build.py --enable-logging --endpoint http --endpoint grpc --backend python`** I built it in the latest...