hexianbin1994

Results 9 issues of hexianbin1994

环境: 系统--windows python3.8 modelscope==1.10.0 模型下载到本地后,设置哪项参数可以加载本地模型,而不是从网络下载。 ```sh pipeline( task=Tasks.auto_speech_recognition, model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online', model_revision='v1.0.6', mode="paraformer_streaming" )

env: os windows python 3.8 opencv==4.5.2.52 when I connect video stream ,it cost more than 1 second to connect ,how to make this time less than 0.5 second ex: ```python...

question

参考 examples/zh_en_tts/tts3 中的语音合成示例,下载了示例中的模型文件,把相关配置改成流式语音的配置项后,调用流式合成能进行部分字母及单词的合成,但有两个问题: 1、部分字母发音不准缺,如A,M,N,I,Z等 2、有非常明显的卡顿感, 这个如何解决? conf 文件: ```sh # This is the parameter configuration file for streaming tts server. ################################################################################# # SERVER SETTING # ################################################################################# host: 0.0.0.0 port: 8190...

Bug
T2S

./run.sh --stage 0 --stop_stage 0 执行至 /workspace/paddlespeech/paddlespeech/t2s/exps/fastspeech2/preprocess.py 287行,提示aishell3 路径缺少/aishell3/train/wav路径,aishell3数据集是从官网下载的,需要怎么样进行划分呢? 这个preprocess.py 之前的也没处理啊 ![image](https://github.com/PaddlePaddle/PaddleSpeech/assets/55222575/369e2893-1492-41a6-a8ae-98e6830443d3)

Bug
T2S

百度网盘的过期了,可以再上传一次模型文件吗?

请教一下,使用海康的SDK连接到rtsp视频流,连接时长可以控制到1秒内吗? 对比使用opencv的连接时长,需要用到3秒以上,拉流延迟较大。 ``` import os os.environ["OPENCV_VIDEOIO_MSMF_ENABLE_HW_TRANSFORMS"] = "0" import cv2,datetime s = "rtsp://admin:ltkj@[email protected]:554/h264/ch1/main/av_stream" print(f"\ncv2.VideoCapture 1 -- time {datetime.datetime.now().strftime('%Y%m%d %H:%M:%S:%f')}") self.cap = cv2.VideoCapture(s) print(f"\ncv2.VideoCapture 2 -- time {datetime.datetime.now().strftime('%Y%m%d %H:%M:%S:%f')}") ``` ```...

做好数据处理等前置工作后,执行训练脚本 python train.py --cfg OWN_config.yaml 提示模型尺寸不正确,示例代码train.py 中构建的三种模型都不正确,如何约束这个尺寸问题? 下面展示各个模型的错误: 1 -- build_lprnet model = build_lprnet(num_classes=len(plate_chr)) 错误为:RuntimeError: Given groups=1, weight of size [64, 3, 3, 3], expected input[32, 1, 32, 160] to...

when I use FFmpegFrameGrabber to capture from rtsp video, I notice the memory will be increase soon, it looks unnormal. os: windows jdk:1.8 javacv:1.5.11-SNAPSHOT ```sh package com.example.demo.server; import lombok.extern.slf4j.Slf4j; import...

help wanted
question

### Expected behaviour opencv-cuda decode rstp video stream success ### Actual behaviour opencv-cuda can decode mp4 video file, but cannot decode rtsp video stream, with the fault is 【Segmentation fault...