pedropauletti
commited on
Commit
•
312ef50
1
Parent(s):
c89d910
End of training
Browse files
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# speecht5_finetuned_common_voice_pt
|
17 |
|
18 |
-
This model is a fine-tuned version of [
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -37,23 +37,24 @@ More information needed
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 1e-05
|
40 |
-
- train_batch_size:
|
41 |
-
- eval_batch_size:
|
42 |
- seed: 42
|
43 |
- gradient_accumulation_steps: 8
|
44 |
-
- total_train_batch_size:
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 500
|
48 |
-
- training_steps:
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: pedropauletti/speecht5_finetuned_common_voice_pt
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
15 |
|
16 |
# speecht5_finetuned_common_voice_pt
|
17 |
|
18 |
+
This model is a fine-tuned version of [pedropauletti/speecht5_finetuned_common_voice_pt](https://huggingface.co/pedropauletti/speecht5_finetuned_common_voice_pt) on the common_voice_11_0 dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4610
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 1e-05
|
40 |
+
- train_batch_size: 4
|
41 |
+
- eval_batch_size: 2
|
42 |
- seed: 42
|
43 |
- gradient_accumulation_steps: 8
|
44 |
+
- total_train_batch_size: 32
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 500
|
48 |
+
- training_steps: 4000
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 0.4962 | 6.58 | 1000 | 0.4737 |
|
55 |
+
| 0.4823 | 13.16 | 2000 | 0.4651 |
|
56 |
+
| 0.4824 | 19.74 | 3000 | 0.4612 |
|
57 |
+
| 0.4845 | 26.32 | 4000 | 0.4610 |
|
58 |
|
59 |
|
60 |
### Framework versions
|