I have checked inside the parent folder jasper
as per:
but there is no file. Also I tried both with and without min_epochs
param but the finetuning did not proceed after epoch 0
in both cases the container was shut down without any err
I have checked inside the parent folder jasper
as per:
but there is no file. Also I tried both with and without min_epochs
param but the finetuning did not proceed after epoch 0
in both cases the container was shut down without any err
Can you login the tlt docker directly and check?
$ tlt speech_to_text run /bin/bash
#
ls /results/jasper/finetune/
More, if you resume training, the previous result will be saved into the folder which has name like “run_0”, “run_1” ,etc.
root@397da11fff01:/workspace/tlt/samples# ls /results/jasper/finetune/
ls: cannot access '/results/jasper/finetune/': No such file or directory
there is no finetune folder at all inside the container
According to your command " -r $RESULTS_DIR/jasper/finetune " , please check where you saved your result.
Following this to build and deploy jasper with a KenLM model but I am not able to find the configuration to follow for best latency and best throughput like it’s mentioned for Citrinet. In citrinet also what does the --vocab_filename
parameter imply ? Training KenLM model on custom corpus generates only kenlm_model binary and there is no vocab_file generated. Please help here. Thanks!
Please create a new forum topic. Thanks.