Hello , i m training model, with my words and dictionary, its decreasing untill 0. 9 but after that increasing again
Please share as text. Please document your training parameters and context. The value of the loss is highly dependant on your datasets.
!python -u DeepSpeech.py \
--train_files /content/drive/My\ Drive/deepSpeech/words.csv \
--test_files /content/drive/My\ Drive/deepSpeech/test/test.csv \
--train_batch_size 82 \
--test_batch_size 11 \
--n_hidden 1000 \
--epochs 3000 \
--scorer /content/drive/My\ Drive/deepSpeech/uzbek.scorer \
--export_dir /content/deepspeech/uzbek/model/ \
--checkpoint_dir /content/deepspeech/uzbek/model/ \
--alphabet_config_path /content/drive/My\ Drive/deepSpeech/alphabet.txt \
--automatic_mixed_precision=True \
--learning_rate 0.001 \
"$@"
Care to comment and explain your dataset ? I’ve asked about training parameters and context, you can’t just drop a command line and expect me to do divination.
There is no dev set, so you won’t be able to efficiently train.
Why do you set epochs to 3000, and why do you set n_hidden to 1000 ?
what training parameters ?
i think many epochs gives a finer result, n_hidden also
can you please give me a definitly paramters or options to train ? i dont know the exact proportions of paramteres
No, I can’t, because it depends on your dataset. And you still have not shared informations on your dataset. You can’t ask for help and not share context and expect people to help you.
Please read and document yourself on machine learning.
what do you mean with dataset ? my audio and text files ? i will give you any dataset, bu i dont get what do you mean with datasets ?
Yes. Also, why don’t you give a dev set. You can’t train seriously without
https://drive.google.com/open?id=1BDWNbsqSnrYw1i3MqfO4r0Is312DgfWu Here is datasets csv
https://drive.google.com/open?id=1X5wHUui0BPDRaxnOOAMtOTn5t3UFfUBv here is my audios
what parameters needed ? and what proportions ? epochs, n_hidden, learning_rate, drop_out_rate ? Where can i find informations about these paramateres ?
You misunderstood me. I don’t have the time to examinate your dataset. Please explain it.
Have you read the documentation ? They are documented. You also really need to get some experience on machine learning.
@Akmal_Nodirov This is really getting tiring now, though. You have not explained why you don’t have a dev set on your training.
Brother, i dont really understand you, how to explain my datasets, i ll try:
i have 93 phrases, not single words. Phrases like “Hello this is me”, “My name is someone” and so on.i I gave 10 of them to test, and another ten 10 dev set, leaving 73 for train like:
–train_batch_size 73 *
** --test_batch_size 10 *
** --dev_batch_size 10 **
** --n_hidden 100 **
** --epochs 200 **
and i have .wav audio file for every phrase
this is what youre asking of datasets ?
Ok, so very very small, hand-crafted dataset. Now we progress. How much audio does that make, in time? One hour?
What kind of use-case do you target ?
the audios are 10 minutes long. All audios are 10 minutes
Ok, so you have roughly 15 hours ? 10*93 makes 930 mins.