first commit; melgan support (perhaps bloated)

I copied this from my old and messy `tacotron-melgan` repo, where I had
previously experimented with running the two models in a pipeline.

I'll be moving over all the JIT pieces here and cleaning up when I can.
This commit is contained in:
Brandon Thomas
2020-06-02 02:17:16 -04:00
commit 72dd12b460
10 changed files with 502 additions and 0 deletions
+7
View File
@@ -0,0 +1,7 @@
jit-models
==========
This project exists to turn PyTorch models into Torch JIT, which can be run in
any language with libtorch bindings.