deepspeech

deepspeech copied to clipboard

How to get the output from one .wav file

9

I would like to know, is there any method to directly parse the wav file and get the output of the model as a text file, without using any manifest...

saikishor

Hi, Just wanting to know if the Nervana Hardware support for RNNs means that its likely that Movidius chips will accelerate things like Mozilla DeepSpeech as well? https://github.com/mozilla/DeepSpeech I am...

madhavajay

AssertionError while evaluating model Zoo pre-trained librispeech model

1

Environment: python 2.7, CUDA 8.0 Command Executed: python evaluate.py --manifest val:dev-clean.csv --model_file librispeech_16_epochs.prm 2017-11-13 13:38:52,729 - neon.backends - WARNING - deterministic_update and deterministic args are deprecated in favor of specifying...

shaofushih

nan cost

8

hi, I'm getting nan cost after resuming the training for the pre-trained model (librispeech_16_epochs.prm). the cost becomes **nan** after 16/17 epoch and the testing results (after each epoch) are null....

basant-kumar

No module named builtins

1

I'm executing 'python train.py --manifest train:train-clean-100/train100manifest.csv --manifest val:dev-clean/devcleanmanifest.csv -e 1 -z 128' on 'neon' directory, but i constantly get the same error: 'No module named builtins'. I've already tried: sudo...

byuns9334

Evaluation issue with new data

1

When I am trying to evaluate with the new data. I find it too complex and finally ended up with error. Ay idea? 2017-10-12 21:51:54,705 - neon.backends - WARNING -...

saikishor

Evaluating Deep Speech 2 on Mac OSX

35

Hello! Thanks for posting this. I'm excited to run speech recognition on files! I've been trying to use Deep Speech 2 for evaluating my denoising pipeline. However, I'm having some...

karllab41

Validation result for a single file is not stable

4

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...

duongquangduc

training process is killed because OOM

4

I have trained neon for librispeech data. But it's always killed because OOM. My machine has 24GB memory and GeForce GTX 1070 card of 8G memory. I found this msg...

fancyerii

Error in utils.py when evaluating

1

Hello, I am using evaluating using the following command: `python evaluate.py --manifest val:/path/to/manifest.csv --model_file /path/to/librispeech_16_epochs.prm --use_wer --inference_file /path/to/results.pkl` I get the following error: ```ssh Traceback (most recent call last): File...

stingerpk