hzgdeerHo

Results 25 comments of hzgdeerHo

[Usage] return tensor.to(device, non_blocking=non_blocking) NotImplementedError: Cannot copy out of meta tensor; no data!

Another way to run this model also failed and got OOM on this hardware configuration :CUDA_VISIBLE_DEVICES=0,1,2,3 python3 -m sglang.launch_server --model-path liuhaotian/llava-v1.6-34b --tokenizer-path liuhaotian/llava-v1.6-34b-tokenizer --port 30000 --tp 2

Can not recognize the audio stream correctly in demo

Huawei Mate 30 5G. And always got some incorrect recognition , If I used if (model.isEndpoint()) { model.reset(). But if (model.isEndpoint()) { model.reset(true).. It will be better ,but sometime I...

Can not recognize the audio stream correctly in demo

THANKS

Can not recognize the audio stream correctly in demo

I tried in Xiaomi PAD , ![0cd02a5303b42845dd6e1692367600b](https://github.com/k2-fsa/sherpa-ncnn/assets/145191076/ee1b2d6c-ea91-4ef8-9b11-0c448ad4dbd9)

Can not recognize the audio stream correctly in demo

会漏话，漏了很多话，没有识别出来。然后if (model.isEndpoint()) { model.reset(). 还是： But if (model.isEndpoint()) { model.reset(true) 比较合适？很严重，你给的版本更严重CPU版本的可能，漏了很多语音没有识别出来

Can not recognize the audio stream correctly in demo

https://github.com/k2-fsa/sherpa-ncnn/assets/145191076/a52d9597-0e47-45b1-947c-79475523a37e

Can not recognize the audio stream correctly in demo

感谢！

Can not recognize the audio stream correctly in demo

直接使用你的原装APP，也不行，有可能你的算法中存在VAD检测导致的话头经常不被识别

Can not recognize the audio stream correctly in demo

别人测试的效果更不好

Can not recognize the audio stream correctly in demo

我发现有个2022年的模型不会出现这个问题，但是，识别的精准度很差。if (model.isEndpoint()) { model.reset().这种方式重置，识别的明显不能用。But if (model.isEndpoint()) { model.reset(true) 还是可以用。十个句子有两个有问题。