Validation result for a single file is not stable

[duongquangduc]

I trained Librispeech data set of 960 hours for a week and got WER at 38% and CER at 12% with the validation data set dev-clean. My issue is, when I verified a single audio file randomly in the validation data set, the output result is quite different compared to the result evaluated from the whole data set.

For example, the transcript of audio file 84-121123-0007.flac is 'WHAT DO YOU MEAN SIR'.
The transcript when evaluated from one sample 84-121123-0007.flac is 'AP WHA E MA EMSIR ', cer is 70% and wer is 100% , while the one from dev-clean set is 'WHAT DOYOU MEAN SIR'.

Could you please suggest?

[Neuroschemata]

Please post the exact command you used to train the model so that we can help diagnose.

[duongquangduc]

@Neuroschemata,
This is the statement to train the model:
python train.py --manifest train:/root/deepspeech/librispeech/train-clean-100/1000_hour_manifest.csv --manifest val:/root/deepspeech/librispeech/train-clean-100/val-manifest.csv -e7 -z32 -s /deepspeech/speech/model_ds2.pkl --model_file /deepspeech/speech/model_ds2.pkl

[tyler-nervana]

This issue is likely related to a bug in model serialization: NervanaSystems/neon#359. We are working on a fix and will give you instructions on how to update when we get one out. Thanks for catching it!

[duongquangduc]

Hi @tyler-nervana,
Is there any update for this request?
Btw, do I need to retrain a new model when it is updated?
Thanks!