jichaoqun

server can not get EOS

1

when i run this :python kaldigstserver/client.py -r 8192 test/data/bill_gates-TED.mp3 I have get: Audio sent, now sending EOS Received error from server (status 1) who can tell me why and what...

INTEL MKL ERROR: /opt/intel/mkl/lib/intel64/libmkl_avx2.so: undefined symbol: mkl_sparse_optimize_bsr_trsm_i8. Intel MKL FATAL ERROR: Cannot load libmkl_avx2.so or libmkl_def.so.

2

when i do this "python kaldigstserver/worker.py -u ws://localhost:8888/worker/ws/speech -c sample_worker.yaml",I have get this problems: INTEL MKL ERROR: /opt/intel/mkl/lib/intel64/libmkl_avx2.so: undefined symbol: mkl_sparse_optimize_bsr_trsm_i8. Intel MKL FATAL ERROR: Cannot load libmkl_avx2.so or libmkl_def.so....

RuntimeError: Given groups=1, weight of size [256, 512, 1, 1], expected input[32, 1024, 10, 10] to have 512 channels, but got 1024 channels instead

help for the mobilenet backone config .yml

1

when i use the mobilenet for backone ,I get some error, the mobilenet have output(1,2,4,6)conv,but the channels can not alignment.So who can give me a config for mobilenet.

微调token长度的问题

2

在微调baichuan2-7B-Base模型的时候，发现，输入的token长度不能超过512，其官方给出的最大长度为4096。 微调遵循官方教程，使用lora的方式，在微调过程中使用官方数据集，在数据中添加超长数据时出现 Token indices sequence length is longer than the specified maximum sequence length for this model (1759 > 512). Running this sequence through the model will result in indexing...