zhifu gao comments

Results 173 comments of


                                            zhifu gao

docker deploy memory will not be released after continuous recognition

Would you please test it with cpp-client? We do not good at java.

基于damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch模型微调,运行finetune.py报错

Please check the wav file carefully. Firstly, the wav path exists or not. Secondly, the duration of wav is longer than 25ms.

小视频可以分析，大视频报错

Please raise a issue as https://github.com/alibaba-damo-academy/FunASR/issues/1074

如何反馈问题

English template, please ref to https://github.com/alibaba-damo-academy/FunASR/issues/1073

不同词典大小的微调

You can check if 200 word lists are included in the 8404 word list. If all of them are included, you can directly proceed with finetuning. If there are words...

使用paraformer进行ASR时无法正确获取模型

Do you use any multi-theads to decode with the pipeline?

执行ASR任务时发生missing 1 required positional argument的错误

Solution: https://github.com/RVC-Boss/GPT-SoVITS/issues/194#issuecomment-1910205929

CT-Transformer标点模型的训练代码没有样例呢，求助！！！

On going

同一mp4重复运行，spk结果不一样

Please update you mp4

微调会自动删除ep文件, 导致微调结束后找不到需要ep文件

try to keep `++train_conf.keep_nbest_models` equals `++train_conf.avg_nbest_model`.