Daniel Oh comments

Results 7 comments of


                                            Daniel Oh

Great work! How to make PPG features?

@hhguo Thanks for your reply! Can you add more details regarding PPG features? What kind of ASR tool did you use and what hidden vectors are you talking about?

Great work! How to make PPG features?

@hhguo Can I ask which ASR model did you exploit? Isn't it from Kaldi?

RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

It is giving errors in the middle of training. This is my training script. I put all other settings in `train.yaml`. ``` python ./openspeech_cli/hydra_train.py dataset.dataset_path=/home/jun1.oh/ dataset.dataset_download=False dataset.manifest_file_path=/home/jun1.oh/LibriSpeech_daniel/libri_subword_manifest.txt tokenizer.vocab_path=/home/jun1.oh/LibriSpeech_daniel/ trainer.batch_size=16 ```...

RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)`

@sooftware Which GPU did you use or recommend?

RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)`

@sooftware Openspeech github 만드실때 혹시 어떤 gpu를 주로 쓰셨었나요?

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

@yinruiqing @sooftware I am using Docker Env. Should I use Conda always? I moved to AZURE server where I have plenty of memory and larger GPU but my model is...

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

@yinruiqing @sooftware ``` [2021-09-29 06:48:48,012][openspeech.utils][INFO] - Processor : x86_64 [2021-09-29 06:48:48,013][openspeech.utils][INFO] - device : Tesla V100-PCIE-16GB [2021-09-29 06:48:48,013][openspeech.utils][INFO] - CUDA is available : True [2021-09-29 06:48:48,013][openspeech.utils][INFO] - CUDA version :...