FileNotFoundError: [Errno 2] No such file or directory: '../../../LibriSpeech/sp.model'

[tand22]

❓ Questions & Help

Getting stuck at this point when trying to run training. Does my shell command look correct?

Details

[sooftware]

Can you attach the command?

[tand22]

python ./openspeech_cli/hydra_train.py dataset=librispeech dataset.dataset_download=False dataset.dataset_path=/home/tand/Projects/openspeech/libri/LibriSpeech dataset.manifest_file_path=/home/tand/Projects/openspeech/libri/LibriSpeech/libri_subword_manifest.txt tokenizer=libri_subword model=rnn_transducer audio=fbank lr_scheduler=warmup_reduce_lr_on_plateau trainer=gpu criterion=cross_entropy

I had some issues downloading the dataset initially, so I manually copied across the contents into train-960 from the other folders.

[sooftware]

Can you show me the head(5 examples) of the libri_subword_manifest.txt?

[sooftware]

Do it without specifying the dataset.manifest_file_path.

[tand22]

Hmm I don't have a libri_subword_manifest.txt. Just tried without specifying the dataset.manifest_file_path and unfortunately it's still the same error.

[tand22]

Managed to solve the issue by moving the LibriSpeech directory up a level