thank you for sharing the code ! how can i train librispeech dataset on this mpdel

silversparro / wav2letter.pytorch

A fully convolution-network for speech-to-text, built on pytorch.

MIT License

126 stars 23 forks source link

thank you for sharing the code ! how can i train librispeech dataset on this mpdel #4

Closed ahmedbhna closed 5 years ago

vaibhav0195 commented 5 years ago

Hi, to train on any dataset, you just need to make train and validation csv file. the content of the csv files should be 'full/path/to/audio.wav','transcription of audio' and then specify these csv files in train.py args along with the sample rate of your audios. :)