Open Rootian opened 4 years ago
Are you running this on librispeech data (because in config your train data are specified as train-clean-100.lst)? Could you show the running command itself and the full log after you run the command (seems you are training from scratch, not finetuning the model)?
Am I able to use audio samples in wav format for CTC criterion? In example, it was shown that flac is used for CTC, so my question is can I use wav for CTC ? @tlikhomanenko
Yep, wav format is supported, feel free to use it (for example TIMIT recipe with wav files)
I solved Loss has NaN values issue by reducing lr to 0.001 @Rootian link for reference: https://github.com/facebookresearch/wav2letter/issues/334
Thanks @tlikhomanenko I will try training using ctc criterion for wav file
Hi, I'm using the fork command on am_resnet_ctc_librispeech_dev_other.bin to adapt the model to my own dataset, and i got the following errors which says
Loss has NaN values.
i tried to debug the source code, the audio samples and list file were read into the
trainset
successfully could you help me find out the problem?and here is my train.cfg:
i've tried setting
--iter
to 10000000 or set other params astrain_am_transformer_ctc.cfg
in sota/2019/librispeech, but i still got the same error