I’m not sure how but your install is very broken. This is basically a “smoke test” that every one of our PR’s has to pass.
If I were you, I’d check everything out from scratch and follow the README instructions again.
I’m not sure how but your install is very broken. This is basically a “smoke test” that every one of our PR’s has to pass.
If I were you, I’d check everything out from scratch and follow the README instructions again.
Are we suppose to train the model while activating the virtual environment ?
It’s recommended that you use a virtual environment.
I followed the github guideline throughout and working on 0.4.1 master.
I also got the exported model with best validation loss.
Installation:
Linux: 16.04 LTS
CUDA 9.0
CUDNN= 7.1.3
Python 3.6.3
DeepSpeech 0.4.1 master
requirements.txt installed. but Tensorflow-gpu ==1.12.0
Installed LFS from the link given on github
Bazel 0.5.1
Downloaded and checked the pre-trained model from Common voice utterances and results are almost 99%
install CTC
Data prepared in CSV format.
Build the native client
have language model prepared from KenLM, generate trie file.
There is no error I got in training and got the .pb model in the end and also results gave me WER though it doesn’t have anything in decoded output.
Please let me know where I am doing wrong,
Thank you for all the help.
There are many steps here and a problem can creep in anywhere.
To help in debugging can you supply the final training log?
the data is in utf-8 and I believe, DeepSpeech support it. Isn’t ?
If I trained on 5-6 files, I got one word decode, but if I trained on a big corpus of 100 hours, nothing decoded.
Thank you so much.
I asked for the log, what’s printed out as training runs.
I will share my next iteration result, which has short utterances.
I believe, if one doesn’t have a lot of data (like thousands of hours), it wouldn’t work on long utterances. Isn’t ?
Is it possible to show the entire log? Including the command that’s running?
WER: 1.000000, CER: 89.000000, loss: 299.336792
I Exporting the model…
I Models exported at /home/rc/Desktop/0.4.1/DeepSpeech-master/exporth
You have to speficy the alphabet_config_path
and lm_binary_path
which indicate the alphabet used and the path to the language model respectively. If you don’t, it uses default values for these which are both for English.
I did that in flags.py
WER: 0.000000, CER: 0.000000, loss: 27.773754
I Exporting the model…
I Models exported at /home/rc/Desktop/0.4.1/DeepSpeech-master/exporth
I got the smoke test passed, I didn’t placed the english language model and trie file.
Meanwhile, I realized, there must be some issue with my language model and trie.
Please share some recommended guideline for language model and trie file. Thank you!
@kdavis Kindly recommend some guideline for language model and trie file making.
I am using DeepSpeech 0.4.1 and probably my native client is not compatible with deepspeech (I think I am using native client of 0.2.1) . My trie file which I build, is binary file but I am thinking it may causes issues or not compatible with decoding.
Or Please refer native client installation guide for DeepSpeech 0.4.1
Thank you!