Repository files navigation

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

Replacescaffe-speech-recognition, see there for some background.

This (relatively) old project is NO LONGER UP TO DATE.
The tensorflow 1.0 used is not compatible anymore and the theory is no longer state of the art either.
We highly recommend you check out and usewhisper

They achieve gooderror rates. Free Speech is in good hands, gothere if you are an end user.For nowthis project is only maintained for educational purposes.

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 (100GBhere and 21GBhere 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, Karen uttering 'zero' with 160 words per minute.

git clone https://github.com/pannous/tensorflow-speech-recognitioncd tensorflow-speech-recognitiongit clone https://github.com/pannous/layer.gitgit clone https://github.com/pannous/tensorpeers.git

git clone  https://git.assembla.com/portaudio.git./configure --prefix=/path/to/your/localmakemake installexport LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/path/to/your/local/libexport LIDRARY_PATH=$LIBRARY_PATH:/path/to/your/local/libexport CPATH=$CPATH:/path/to/your/local/includesource ~/.bashrc

pip install pyaudio

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

Some less trivial architectures:./densenet_layer.py

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

Update: Nervanademonstrated that it is possible for 'independents' to build speech recognizers that are state of the art.

• Watch video :https://www.youtube.com/watch?v=u9FPqkuoEJ8
• Understand and correct the corresponding code:lstm-tflearn.py
• Data Augmentation : create on-the-fly modulation of the data: increase the speech frequency, add background noise, alter the pitch etc,...

Extensions to current tensorflow which are probably needed:

• WarpCTC on the GPU seeissue
• Incremental collaborative snapshots ('P2P learning') !
• Modular graphs/models + persistance

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 toinfo@pannous.com