deepvoice3_pytorch
deepvoice3_pytorch copied to clipboard
r9y9
PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
Basically what the title says. I am experimenting with multi-speaker adaptation to unseen speakers and my setup has 4 cores. I was wondering if I could use the pipeline to...
I have built pytorch 1.4 from source. When I run `pip install --user -e ".[bin]"`, it tries to download torch 1.3 and I don't want that. ``` $ pip install...
the custom voice I trained has a hard time completing utterances. My input audio samples are not clipped so I'm at a loss why this is. Anyone have any thoughts?...
I'd like to train this model on 8 V100 GPUs - does it support multi GPU training?
Hi, in Deep Voice 3, the frontend for English converts input words to their phoneme representations at a certain probability, say 50% for training. I found two patterns in which...
Noticed while working on https://github.com/r9y9/deepvoice3_pytorch/pull/21. Trained 300k steps, but the model was not generalized well. Need to figure out how we can improve.
the package adds all popular nltk packages so that code does not error out when it does not find cmudict or the punkt package.
Even if hparams is changed in preset file, the inner workings of audio.py doesn't follow the preset file. My experiment had shown that while the changed hparams due to preset...
I was able to run the "python3.5 synthesis.py ....". But it generated an error at the end each time. .............................. Finished! Check out ./output for generated audio samples. *** Error...
