Latest model configuration is not compatible with master

[Mic92]

I tried https://drive.google.com/open?id=10ymOlWHutqTtfDYhIbHULn2IKDKP0O9m
with master and got the following error:

$ python -m TTS.server --pwgan_config ./pwgan/config.json --pwgan_file ./pwgan/best_model.pth.tar --tts_config ./tts/config.json --tts_checkpoint ./tts/best_model.pth.tar 

  19   │     Missing key(s) in state_dict: "encoder.convolutions.0.convolution1d.weight", "encoder.convolutions.0.convolution1d.bias", "encoder.convolutions.0.batch_normaliz
       │ ation.weight", "encoder.convolutions.0.batch_normalization.bias", "encoder.convolutions.0.batch_normalization.running_mean", "encoder.convolutions.0.batch_normaliza
       │ tion.running_var", "encoder.convolutions.1.convolution1d.weight", "encoder.convolutions.1.convolution1d.bias", "encoder.convolutions.1.batch_normalization.weight",
       │ "encoder.convolutions.1.batch_normalization.bias", "encoder.convolutions.1.batch_normalization.running_mean", "encoder.convolutions.1.batch_normalization.running_va
       │ r", "encoder.convolutions.2.convolution1d.weight", "encoder.convolutions.2.convolution1d.bias", "encoder.convolutions.2.batch_normalization.weight", "encoder.convol
       │ utions.2.batch_normalization.bias", "encoder.convolutions.2.batch_normalization.running_mean", "encoder.convolutions.2.batch_normalization.running_var", "decoder.pr
       │ enet.linear_layers.0.linear_layer.weight", "decoder.prenet.linear_layers.0.batch_normalization.weight", "decoder.prenet.linear_layers.0.batch_normalization.bias", "
       │ decoder.prenet.linear_layers.0.batch_normalization.running_mean", "decoder.prenet.linear_layers.0.batch_normalization.running_var", "decoder.prenet.linear_layers.1.
       │ linear_layer.weight", "decoder.prenet.linear_layers.1.batch_normalization.weight", "decoder.prenet.linear_layers.1.batch_normalization.bias", "decoder.prenet.linear
       │ _layers.1.batch_normalization.running_mean", "decoder.prenet.linear_layers.1.batch_normalization.running_var", "decoder.attention.location_layer.location_conv1d.wei
       │ ght", "postnet.convolutions.0.convolution1d.weight", "postnet.convolutions.0.convolution1d.bias", "postnet.convolutions.0.batch_normalization.weight", "postnet.conv
       │ olutions.0.batch_normalization.bias", "postnet.convolutions.0.batch_normalization.running_mean", "postnet.convolutions.0.batch_normalization.running_var", "postnet.
       │ convolutions.1.convolution1d.weight", "postnet.convolutions.1.convolution1d.bias", "postnet.convolutions.1.batch_normalization.weight", "postnet.convolutions.1.batc
       │ h_normalization.bias", "postnet.convolutions.1.batch_normalization.running_mean", "postnet.convolutions.1.batch_normalization.running_var", "postnet.convolutions.2.
       │ convolution1d.weight", "postnet.convolutions.2.convolution1d.bias", "postnet.convolutions.2.batch_normalization.weight", "postnet.convolutions.2.batch_normalization
       │ .bias", "postnet.convolutions.2.batch_normalization.running_mean", "postnet.convolutions.2.batch_normalization.running_var", "postnet.convolutions.3.convolution1d.w
       │ eight", "postnet.convolutions.3.convolution1d.bias", "postnet.convolutions.3.batch_normalization.weight", "postnet.convolutions.3.batch_normalization.bias", "postne
       │ t.convolutions.3.batch_normalization.running_mean", "postnet.convolutions.3.batch_normalization.running_var", "postnet.convolutions.4.convolution1d.weight", "postne
       │ t.convolutions.4.convolution1d.bias", "postnet.convolutions.4.batch_normalization.weight", "postnet.convolutions.4.batch_normalization.bias", "postnet.convolutions.
       │ 4.batch_normalization.running_mean", "postnet.convolutions.4.batch_normalization.running_var".
  20   │     Unexpected key(s) in state_dict: "encoder.convolutions.0.net.0.weight", "encoder.convolutions.0.net.0.bias", "encoder.convolutions.0.net.1.weight", "encoder.con
       │ volutions.0.net.1.bias", "encoder.convolutions.0.net.1.running_mean", "encoder.convolutions.0.net.1.running_var", "encoder.convolutions.0.net.1.num_batches_tracked"
       │ , "encoder.convolutions.1.net.0.weight", "encoder.convolutions.1.net.0.bias", "encoder.convolutions.1.net.1.weight", "encoder.convolutions.1.net.1.bias", "encoder.c
       │ onvolutions.1.net.1.running_mean", "encoder.convolutions.1.net.1.running_var", "encoder.convolutions.1.net.1.num_batches_tracked", "encoder.convolutions.2.net.0.wei
       │ ght", "encoder.convolutions.2.net.0.bias", "encoder.convolutions.2.net.1.weight", "encoder.convolutions.2.net.1.bias", "encoder.convolutions.2.net.1.running_mean",
       │ "encoder.convolutions.2.net.1.running_var", "encoder.convolutions.2.net.1.num_batches_tracked", "decoder.prenet.layers.0.linear_layer.weight", "decoder.prenet.layer
       │ s.0.bn.weight", "decoder.prenet.layers.0.bn.bias", "decoder.prenet.layers.0.bn.running_mean", "decoder.prenet.layers.0.bn.running_var", "decoder.prenet.layers.0.bn.
       │ num_batches_tracked", "decoder.prenet.layers.1.linear_layer.weight", "decoder.prenet.layers.1.bn.weight", "decoder.prenet.layers.1.bn.bias", "decoder.prenet.layers.
       │ 1.bn.running_mean", "decoder.prenet.layers.1.bn.running_var", "decoder.prenet.layers.1.bn.num_batches_tracked", "decoder.attention.location_layer.location_conv.weig
       │ ht", "postnet.convolutions.0.net.0.weight", "postnet.convolutions.0.net.0.bias", "postnet.convolutions.0.net.1.weight", "postnet.convolutions.0.net.1.bias", "postne
       │ t.convolutions.0.net.1.running_mean", "postnet.convolutions.0.net.1.running_var", "postnet.convolutions.0.net.1.num_batches_tracked", "postnet.convolutions.1.net.0.
       │ weight", "postnet.convolutions.1.net.0.bias", "postnet.convolutions.1.net.1.weight", "postnet.convolutions.1.net.1.bias", "postnet.convolutions.1.net.1.running_mean
       │ ", "postnet.convolutions.1.net.1.running_var", "postnet.convolutions.1.net.1.num_batches_tracked", "postnet.convolutions.2.net.0.weight", "postnet.convolutions.2.ne
       │ t.0.bias", "postnet.convolutions.2.net.1.weight", "postnet.convolutions.2.net.1.bias", "postnet.convolutions.2.net.1.running_mean", "postnet.convolutions.2.net.1.ru
       │ nning_var", "postnet.convolutions.2.net.1.num_batches_tracked", "postnet.convolutions.3.net.0.weight", "postnet.convolutions.3.net.0.bias", "postnet.convolutions.3.
       │ net.1.weight", "postnet.convolutions.3.net.1.bias", "postnet.convolutions.3.net.1.running_mean", "postnet.convolutions.3.net.1.running_var", "postnet.convolutions.3
       │ .net.1.num_batches_tracked", "postnet.convolutions.4.net.0.weight", "postnet.convolutions.4.net.0.bias", "postnet.convolutions.4.net.1.weight", "postnet.convolution
       │ s.4.net.1.bias", "postnet.convolutions.4.net.1.running_mean", "postnet.convolutions.4.net.1.running_var", "postnet.convolutions.4.net.1.num_batches_tracked".

Here is the full backtrace:
log.txt

How can I test things on master? I don't have the resources to train my own models.

Update The latest commit that works for me is around 53b2462

[Mic92]

Ok. 1d3c0c8 also does not work. Maybe its a different problem than.

[lexkoro]

Did you use the branch https://github.com/mozilla/TTS/tree/20a6ab3 linked in the wiki?

[Mic92]

@sanjaesc it works with 20a6ab3. However my point is that there should be always at least one model working with master. Otherwise the library is broken and no one except insiders can work with it.

[reuben]

The library is under active development. If you don't have resources to train your own model, then stick to a commit that matches a pre-trained model. It's quite simple.

[reuben]

Closing because there is no guarantee of master compatibility for releases.

[Mic92]

The library is under active development. If you don't have resources to train your own model, then stick to a commit that matches a pre-trained model. It's quite simple.

How do I contribute fixes than if I am stuck on old code? For example I fixed vocoder on a older revision but I cannot test if it is still broken in newer versions. How do you do unit testing if you don't have a working model?

[reuben]

Due to constant architectural changes it's not feasible to keep an updated model always available for master. We train a small testing model for unit tests. For behavioral fixes I guess there's no other way around training a model to see if it still applies.

[erogol]

@Mic92 There is a dummy model we use for unit testing. You can see it under tests folder. It just does random predictions as it is used for server and model inference tests. If you have a better suggestion I'd be happy to hear