yunigma

Hello @upskyy ! Thank you very much for your response. Change ```cross_entropy``` to ```transducer``` helped to fix the issue reported above. I managed to start training, yet the training loss...

Hello, @upskyy ! I have tried setting ```accumulate_grad_batches``` to 8 but it made loss grow even faster...

Thank you @upskyy !! No worries. It is a very cool project anyway. I keep trying to understand the issue on my side too.

Hello I guess I have the same issue with ```model: model_name: contextnet_lstm model_size: medium input_dim: 80 num_encoder_layers: 5 num_decoder_layers: 2 kernel_size: 5 num_channels: 256 encoder_dim: 640 num_attention_heads: 8 attention_dropout_p: 0.1...

@resurgo97 hello. Did you manage to fix this issue finally? Thanks. Iuliia

Hi @sooftware . Attach here. Thank you! [logs_20220201_2.log](https://github.com/openspeech-team/openspeech/files/7984853/logs_20220201_2.log)

Thank you!! ```python ./openspeech_cli/hydra_train.py dataset=librispeech dataset.dataset_download=False dataset.dataset_path="../../../../database/LibriSpeech/" dataset.manifest_file_path="../../../openspeech/datasets/librispeech/libri_subword_manifest.txt" tokenizer=libri_subword model=contextnet_lstm audio=fbank lr_scheduler=warmup_reduce_lr_on_plateau trainer=gpu criterion=cross_entropy```

@upskyy thank you very much for testing! Do you think that the training can improve slower with the librispeech dataset? Or there is some error in the training itself?

Hi @upskyy ! I have finally tried to reproduce the same setup but with librispeech. ``` python ./openspeech_cli/hydra_train.py dataset=librispeech \ dataset.dataset_download=False \ dataset.dataset_path="../database/LibriSpeech/" \ dataset.manifest_file_path="../../../openspeech/datasets/librispeech/libri_char_manifest.txt" \ tokenizer=libri_character \ model=contextnet \...

Probably, otherwise CER would also go down... But CER was not improving much either. Do you know how long @upskyy was training and with which parameters? Here is my logs:...