pannous / tensorflow-speech-recognition

🎙Speech recognition using the tensorflow deep learning framework, sequence-to-sequence neural networks
Other
2.17k stars 638 forks source link

Data for CTC in lstm to chars. #38

Open TsainGra opened 7 years ago

TsainGra commented 7 years ago

The data directory given for ctc data in the lstm_to_chars.py file is given as - INPUT_PATH = '/data/ctc/sample_data/mfcc' # directory of MFCC nFeatures x nFrames 2-D array .npy files Where can I find the data (since it is not available in speech_data.py)?