Eric

您好，有两个问题，可以帮忙看下么？ 1、开启 `jieba.enable_parallel(multiprocessing.cpu_count())` 之后，use_paddle=True会报没有这个参数的错。 2、开启use_paddle或者hmm，add_word自定义字典不起作用 另外提供bathc调用么

[Paddle2ONNX] Oops, there are some operators not supported yet

4

运行如下代码报错了：[Paddle2ONNX] Oops, there are some operators not supported yet，including fake_channel_wise_quantize_dequantize_abs_max,fake_quantize_dequantize_moving_average_abs_max, ```python import fastdeploy as fd import os import cv2 import time option = fd.RuntimeOption() #option.use_openvino_backend() option.use_ort_backend() #option.use_paddle_infer_backend() #option.use_trt_backend() #option.set_trt_cache_file(os.path.join("ppyoloe_crn_l_300e_coco_qat", "model.trt"))...

First thank you for your work "Paraphrastic Representations at Scale"😝. In this paper you said you released trained models for English, Arabic, German, French, Spanish, Russian, Turkish, and Chinese in...

ValueError: AutomaticSpeechRecognitionPipeline: unknown input_layer: pe_online

1

您好，我的环境如下： nvcc -V nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2021 NVIDIA Corporation Built on Mon_May__3_19:15:13_PDT_2021 Cuda compilation tools, release 11.3, V11.3.109 Build cuda_11.3.r11.3/compiler.29920130_0 modelscope 1.4.3 tensorboard 1.15.0 tensorboard-data-server...

提问后，只会返回相关列表给我，并没有生成答案

1

- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions - [X] 我已经搜索过FAQ | I have searched FAQ ### 当前行为 | Current Behavior 我传入了300多本书籍，但是提问后，只会返回相关列表给我，llm并没有在整合排序的资料生成回答，请问这是为什么？ ### 期望行为 | Expected...