search

keithito / tacotron

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
MIT License
2.94k stars 965 forks source link

Update README.md #286

Closed gisforgirard closed 5 years ago

gisforgirard commented 5 years ago

it saves files every 100

keithito commented 5 years ago

It writes stats for tensorboard every 100 iterations, but only dumps the audio and alignment every 1000, so I think the original comment is correct.