Hugging Face's logo

peymansyh
/
speecht5_finetuned_voxpopuli_it

Text-to-Speech
Transformers
PyTorch
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Community
peymansyh commited on
Commit
5d3d743
•
1 Parent(s): 45a58ea

End of training

Browse files
Files changed (3) hide show
  1. README.md +9 -9
  2. pytorch_model.bin +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 0.4841
22
 
23
  ## Model description
24
 
@@ -37,7 +37,7 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 7e-06
41
  - train_batch_size: 4
42
  - eval_batch_size: 2
43
  - seed: 42
@@ -52,13 +52,13 @@ The following hyperparameters were used during training:
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
- | 0.5625 | 4.72 | 1000 | 0.5168 |
56
- | 0.5329 | 9.43 | 2000 | 0.5001 |
57
- | 0.526 | 14.15 | 3000 | 0.4915 |
58
- | 0.5261 | 18.87 | 4000 | 0.4878 |
59
- | 0.5194 | 23.58 | 5000 | 0.4865 |
60
- | 0.5138 | 28.3 | 6000 | 0.4853 |
61
- | 0.5099 | 33.02 | 7000 | 0.4841 |
62
 
63
 
64
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the facebook/voxpopuli dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 0.4790
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 5e-05
41
  - train_batch_size: 4
42
  - eval_batch_size: 2
43
  - seed: 42
 
52
 
53
  | Training Loss | Epoch | Step | Validation Loss |
54
  |:-------------:|:-----:|:----:|:---------------:|
55
+ | 0.5214 | 4.72 | 1000 | 0.4866 |
56
+ | 0.4964 | 9.43 | 2000 | 0.4788 |
57
+ | 0.4843 | 14.15 | 3000 | 0.4780 |
58
+ | 0.4831 | 18.87 | 4000 | 0.4754 |
59
+ | 0.4751 | 23.58 | 5000 | 0.4781 |
60
+ | 0.4692 | 28.3 | 6000 | 0.4790 |
61
+ | 0.4661 | 33.02 | 7000 | 0.4790 |
62
 
63
 
64
  ### Framework versions
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15b7f72b780687ed4e6dee020b27257eb26571e152616578da467e82ef3d308b
3
  size 577878333
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:537023c3e5fda0824814c2bec4ad1a6259f52774d914d40d5474b9589e584250
3
  size 577878333
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5025b08eb0050d32e04a9245d3c9575b145fdd0e7e56c54a01a7e9756889c20a
3
  size 4219
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3bfb54215a71648e08d3abd0ed4541dfd72456cfa9d9e3acad05c5bf7b148de
3
  size 4219