search

keithito / tacotron

A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unofficial)
MIT License
2.96k stars 957 forks source link

Synthesize on Batch #202

Closed raghavgurbaxani closed 6 years ago

raghavgurbaxani commented 6 years ago

Hi

Is is possible to synthesize speech during testing/inference on a batch of inputs ? Thanks.

keithito commented 6 years ago

Yes. But you'll need to modify the synthesizer code a little bit, both where the placeholders are created: https://github.com/keithito/tacotron/blob/master/synthesizer.py#L14

and when the feed dict is populated: https://github.com/keithito/tacotron/blob/master/synthesizer.py#L32

Alvinhech commented 5 years ago

But how to modify the code?