Z-yq / TensorflowASR

一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目,CPU上的实时率(RTF)小于0.1
Apache License 2.0
461 stars 111 forks source link

hi, i re-implement conformer based on your project, when i train conformer with ctc loss on chinese dataset, loss is fluctuating #28

Closed yyht closed 3 years ago

yyht commented 3 years ago

hi, thanks to your peoject, i re-implement conformer for tf.1.15. When i train it with ctc loss on 1000-h chinese audio dataset, the loss is fluctuating and could not decline. the conv-sampling is 3-layer conv2d with 144 filters and kernel_size=3, reduction_factor=4 the conformer is just like the bert-base but with relative position encoding using t-5 the optimizer is adam-with-weight-decay, params are default as bert-base . could you help me with this?

Z-yq commented 3 years ago

you can use adam to try it again.