Good pre-trained weights anyone?
duvtedudug opened this issue · 15 comments
First, thank you very much @r9y9 and everyone for the great work!
Does anyone want to share pre-trained weights that sound good?
Particularly for LJSpeech if possible. My training is to be converging to a very high loss value. I would love to experiment with some sounds, and maybe figure out where I am going wrong in training.
Thanks in advance,
Duvte.
@duvtedudug i have trained ljspeech for 340k, this is the link ljspeech_340k_pth
https://www.dropbox.com/s/8qgcbd1mm2xsqgq/20180127_mixture_lj_checkpoint_step000410000_ema.pth?dl=0
Weights used to generate speech for https://r9y9.github.io/wavenet_vocoder/
@azraelkuan @r9y9
Thank you both very much!
@r9y9 Thanks for the checkpoint! Would it be possible to share the multispeaker checkpoint as well?
Thanks!
Here you are:) This is also the one used for the demo page.
@r9y9 Could you show us the parameters/configurations for this checkpoint(20180212_mixture_multispeaker_cmu_arctic_checkpoint_step000740000_ema.pth). I tried to generate voices with this one, while the results were not as good as what you published.
My command line is as following:
python synthesis.py checkpoint.pth --hparams="input_type=raw,gin_channels=16" --speaker-id=5
One of my results is as following:
@mfkfge Sounds like there's mismatch between mel-spectrogram and speaker ID. Did you use mel-spectrogram of speaker ID 5?
@r9y9 yes. i did try with mel-spectrogram of speaker id 5 as well as that of speaker id 6.
Oh, I see the problem. Can you try with --hparams="input_type=raw,gin_channels=16.sample_rate=16000"? sample_rate is 16kHz for CMU ARCTIC.
I'm also having trouble generating good sound, even with sample_rate=16000.
My cmd line is:
python synthesis.py 20180212_mixture_multispeaker_cmu_arctic_checkpoint_step000740000_ema.pth ./ --conditional=cmu_arctic-mel-00001.npy --preset=20180212_multispeaker_cmu_arctic_mixture.json --symmetric-mels --speaker-id 5 --hparams="sample_rate=16000"
Am I doing the right thing?