Skip to content

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks

License

Notifications You must be signed in to change notification settings

pujoseno/tensorflow-speech-recognition

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Tensorflow Speech Recognition

Speech recognition using google's tensorflow deep learning framework, sequence-to-sequence neural networks.

Replaces caffe-speech-recognition, see there for some background.

Update Mozilla released DeepSpeech

They achieve good error rates. Free Speech is in good hands, go there if you are an end user. For now this project is only maintained for educational purposes.

Ultimate goal

Create a decent standalone speech recognition for Linux etc. Some people say we have the models but not enough training data. We disagree: There is plenty of training data (100GB here and 21GB here on openslr.org , synthetic Text to Speech snippets, Movies with transcripts, Gutenberg, YouTube with captions etc etc) we just need a simple yet powerful model. It's only a question of time...

Sample spectrogram, That's what she said, too laid?

Sample spectrogram, Karen uttering 'zero' with 160 words per minute.

Getting started

Toy examples: ./number_classifier_tflearn.py ./speaker_classifier_tflearn.py

Some less trivial architectures: ./densenet_layer.py

Later: ./train.sh ./record.py

Sample spectrogram or record.py

Partners + collaborators wanted

We are in the process of tackling this project in seriousness. If you want to join the party just drop us an email at info@pannous.com.

Update: Nervana demonstrated that it is possible for 'independents' to build speech recognizers that are state of the art. Update: Mozilla is working on DeepSpeech and just achieved 0% error rate ... on the training set;) Free Speech is in good hands.

Fun tasks for newcomers

Extensions

Extensions to current tensorflow which are probably needed:

Even though this project is far from finished we hope it gives you some starting points.

Looking for a tensorflow collaboration / consultant / deep learning contractor? Reach out to info@pannous.com

About

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 97.6%
  • Swift 2.4%