Hugging Face's logo

Strange18
/
speecht5_tts_voxpopuli_nl

Text-to-Audio
Transformers
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Community
Strange18 commited on
Commit
5dd38e3
·
verified ·
1 Parent(s): d3e28f5

End of training

Browse files
Files changed (3) hide show
  1. README.md +12 -12
  2. model.safetensors +1 -1
  3. training_args.bin +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4700
20
 
21
  ## Model description
22
 
@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
  - total_train_batch_size: 16
44
- - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
  - training_steps: 1000
@@ -51,16 +51,16 @@ The following hyperparameters were used during training:
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 0.7385 | 2.8571 | 100 | 0.6010 |
55
- | 0.5947 | 5.7143 | 200 | 0.5146 |
56
- | 0.5621 | 8.5714 | 300 | 0.4919 |
57
- | 0.5328 | 11.4286 | 400 | 0.4760 |
58
- | 0.541 | 14.2857 | 500 | 0.4724 |
59
- | 0.4935 | 17.1429 | 600 | 0.4688 |
60
- | 0.502 | 20.0 | 700 | 0.4664 |
61
- | 0.5023 | 22.8571 | 800 | 0.4671 |
62
- | 0.4933 | 25.7143 | 900 | 0.4676 |
63
- | 0.4954 | 28.5714 | 1000 | 0.4700 |
64
 
65
 
66
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.4839
20
 
21
  ## Model description
22
 
 
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
  - total_train_batch_size: 16
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
  - training_steps: 1000
 
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 0.8047 | 1.6667 | 100 | 0.6467 |
55
+ | 0.6735 | 3.3333 | 200 | 0.5503 |
56
+ | 0.6013 | 5.0 | 300 | 0.5084 |
57
+ | 0.5619 | 6.6667 | 400 | 0.4996 |
58
+ | 0.5466 | 8.3333 | 500 | 0.4909 |
59
+ | 0.5313 | 10.0 | 600 | 0.4864 |
60
+ | 0.5283 | 11.6667 | 700 | 0.4851 |
61
+ | 0.5372 | 13.3333 | 800 | 0.4846 |
62
+ | 0.5266 | 15.0 | 900 | 0.4855 |
63
+ | 0.5258 | 16.6667 | 1000 | 0.4839 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3f48633f57bdfff787e7cc5ac98ff9cc0097b36e1f3da111ee1ad7d8c04ce53
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be35bbcaf751b0acdd4cfacf69cc7979afff4abf3caf09b2060b7f219060f57d
3
  size 577789320
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d810aaf496bf2a8d258c3452d7c4aacd62d984d10d3ac9ce3d823718ec3b22d
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613cc0cea846cffdeb31e01a343f069eb6a0911ecf4d2b2e65cc5ad5f39bec2d
3
  size 5496