Training results with 0.4.1 far worse than 0.3.0

(Rajpuneet Sandhu) #46

@reuben should I always extend the validation set with my own data instead of just using my validation data set? because otherwise it would over fit, wouldn’t it?

0 Likes

(Reuben Morais) #47

Your validation set should always be representative of the types of audio you want your model to be good at. Otherwise, yes, you risk overfitting.

0 Likes

#48

fewer epochs, smaller learning rate, make sure your dev set is good

0 Likes

(Hafsa Farooq) #49

@rajpuneet.sandhu Can you post a complete guide for training DeepSpeech 0.4.1 ?
Plus guide about which file are required for it ?
How trie can be generated ?
Thank you!

0 Likes

(Rajpuneet Sandhu) #50

checkout ‘How I trained a French robot’. It has all the steps @noor_e_emaan11

0 Likes

(Rajpuneet Sandhu) #51

I trained with TEDlium (from Mozilla common voice website)and Voxforge (using the import script in DeepSpeech repo) datasets with the following:
python3 DeepSpeech.py --n_hidden 2048 --checkpoint_dir ~/deepspeech-0.4.1-checkpoint --epoch -1 --train_files /home/rsandhu/ted-train.csv,/home/rsandhu/voxforge-train.csv --dev_files /home/rsandhu/ted-dev.csv,/home/rsandhu/voxforge-dev.csv,/home/rsandhu/common_voice_training_data/cv-valid-dev.csv,/mnt/librivox_data/librivox-dev-clean.csv,/mnt/librivox_data/librivox-dev-other.csv --test_files /home/rsandhu/ted-test.csv,/home/rsandhu/voxforge-test.csv --learning_rate 0.0001 --train_batch_size 24 --dev_batch_size 48 --test_batch_size 48 --display_step 0 --validation_step 1 --dropout_rate 0.2 --checkpoint_step 1 --lm_alpha 0.75 --lm_beta 1.85 --export_dir ~/new_model

I tested this generated model and the release 0.4.1 model and the results are in the attached filedeepspeech_test_comparison_ted_voxforge.zip (8.2 KB)

The datasets used for training are validated and clean but still I see the performance has degraded significantly. Any thoughts on this?
@lissyx @kdavis @reuben @josh_meyer

0 Likes

(Rajpuneet Sandhu) #52

@lissyx @kdavis @reuben @josh_meyer, did you get a chance to review the results?

0 Likes

(Ramaniaditya22) #53

This is slightly out of context, I’m trying to train a model on the same data set. Could you share your findings and developments?

0 Likes

(Rajpuneet Sandhu) #54

@ramaniaditya22 I was not able to get satisfactory results. What about you?

0 Likes