audio

audio copied to clipboard

The TextProcessor object from TTS pipeline, should be able to return Tensors in specified device.

Currently the returned Tensors have to be manually moved to the target device.

bundle = torchaudio.pipelines.TACOTRON2_WAVERNN_PHONE_LJSPEECH
processor = bundle.get_text_processor()

text = "Hello world! Text to speech!"
processed, lengths = processor(text)
processed = processed.to(device)
lengths = lengths.to(device)

Inheriting torch.nn.Module should make this simpler

bundle = torchaudio.pipelines.TACOTRON2_WAVERNN_PHONE_LJSPEECH
processor = bundle.get_text_processor().to(device)

text = "Hello world! Text to speech!"
processed, lengths = processor(text)