【Help】How to modify the training configuration parameters if my sample duration is 1.5 seconds? Thanks

[xjj210130]

Hi all:
when i use the cmd:
python train.py --model_architecture ds_cnn --model_size_info 5 64 10 4 2 2 64 3 3 1 1 64 3 3 1 1 64 3 3 1 1 64 3 3 1 1 --dct_coefficient_count 10 --window_size_ms 40 --window_stride_ms 20 --learning_rate 0.0005,0.0001,0.00002 --how_many_training_steps 10000,10000,10000 --summaries_dir work/DS_CNN/DS_CNN1/retrain_logs --train_dir work/DS_CNN/DS_CNN1/training

The training data is speech_commands_v0.02. All data time is 1seconds. And use 40 MFCC features extracted from a speech frame of length 40ms with a stride of 20ms, which gives 1960 (49�40) features for 1 second of audio.

However, my own training sample is 1.5 seconds long. When I use the above command to train, which parameters need to be modified?
Thanks very much

[xjj210130]

Only need to modify the parameters clip_duration_ms=1500?

[dimanshu]

@xjj210130 did u solve it ?