Tom Andrews comments

Results 7 comments of


                                            Tom Andrews

Wrong picture orientation on Samsung devices

@ivacf does your code require API level 24? add this stage i'm just considering screenshotting the fking viewfinder. the camera api drives me nuts

Expected period of time hanging(or pre-processing) in the beginning of the training

Also getting this issue, for reference I'm using Ubuntu 20.04.2 and a 2080Ti also. Is there a fix?

Expected period of time hanging(or pre-processing) in the beginning of the training

Seems to have done something, however now getting this. How can I lower the memory usage?

Expected period of time hanging(or pre-processing) in the beginning of the training

Even with a batch size of 1 I'm running out of memory.. might be a memory leak.

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

`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...

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

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.

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

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