wanshun123

What makes a good TTS dataset?

3

I have done a lot of training on different self-made datasets (typically having around 3 hours of audio across a few thousand .wav files, all 22050 Hz) using Tacotron, starting...

Download link for model trained to 877K steps?

1

I've downloaded the pretrained model listed in the readme at http://data.keithito.com/data/speech/tacotron-20180906.tar.gz. This seems to be trained to 441,000 steps as the output when resuming training from it will include something...

Training with custom data

2

Curious if others have achieved reasonable results training on custom data. I've tried training the model on data from https://github.com/aomv/voiceloop-in-the-wild-experiments/tree/master/data/donald-trump/data (which has audio files and transcriptions of a few seconds...

"Debug Error" errors

1

I've copied the `vulnerable.sol` file from the readme and am trying the following commands: ``` solcjs --abi -o output vulnerable.sol solcjs --bin -o output vulnerable.sol $abi = Get-Content .\output\vulnerable_sol_SendBalance.abi $bin...

Other considerations for what makes a good TTS dataset?

1

I have done a lot of training on different self-made datasets (typically having around 3 hours of audio across a few thousand .wav files, all 22050 Hz) using Tacotron, starting...