hugo flores garcia commited on
Commit
9c153c6
1 Parent(s): 1b1b9de

add default model for hf spaces

Browse files
Files changed (3) hide show
  1. DEFAULT_MODEL +1 -0
  2. README.md +3 -0
  3. app.py +3 -0
DEFAULT_MODEL ADDED
@@ -0,0 +1 @@
 
 
1
+ default
README.md CHANGED
@@ -149,6 +149,9 @@ python scripts/exp/train.py --args.load conf/generated/<fine_tune_name>/c2f.yml
149
  This repository relies on [argbind](https://github.com/pseeth/argbind) to manage CLIs and config files.
150
  Config files are stored in the `conf/` folder.
151
 
 
 
 
152
  ### Licensing for Pretrained Models:
153
  The weights for the models are licensed [`CC BY-NC-SA 4.0`](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.ml). Likewise, any VampNet models fine-tuned on the pretrained models are also licensed [`CC BY-NC-SA 4.0`](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.ml).
154
 
 
149
  This repository relies on [argbind](https://github.com/pseeth/argbind) to manage CLIs and config files.
150
  Config files are stored in the `conf/` folder.
151
 
152
+ ### Take a look at the pretrained models
153
+ All the pretrained models (trained by hugo) are stored here: https://huggingface.co/hugggof/vampnet
154
+
155
  ### Licensing for Pretrained Models:
156
  The weights for the models are licensed [`CC BY-NC-SA 4.0`](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.ml). Likewise, any VampNet models fine-tuned on the pretrained models are also licensed [`CC BY-NC-SA 4.0`](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.ml).
157
 
app.py CHANGED
@@ -18,6 +18,9 @@ from vampnet import mask as pmask
18
  device = "cuda" if torch.cuda.is_available() else "cpu"
19
 
20
  interface = Interface.default()
 
 
 
21
 
22
  def to_output(sig):
23
  return sig.sample_rate, sig.cpu().detach().numpy()[0][0]
 
18
  device = "cuda" if torch.cuda.is_available() else "cpu"
19
 
20
  interface = Interface.default()
21
+ init_model_choice = open("DEFAULT_MODEL.txt").read().strip()
22
+ # load the init model
23
+ interface.load_finetuned(init_model_choice)
24
 
25
  def to_output(sig):
26
  return sig.sample_rate, sig.cpu().detach().numpy()[0][0]