flavioegoncalves
commited on
Commit
•
3f4a574
1
Parent(s):
ed4dc00
End of training
Browse files
README.md
CHANGED
@@ -20,7 +20,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the MultilingualLibrispeech dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
-
- Loss: 0.
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -48,17 +48,23 @@ The following hyperparameters were used during training:
|
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
- lr_scheduler_warmup_steps: 500
|
51 |
-
- training_steps:
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
-
| Training Loss | Epoch | Step
|
57 |
-
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
|
63 |
|
64 |
### Framework versions
|
|
|
20 |
|
21 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the MultilingualLibrispeech dataset.
|
22 |
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 0.3452
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
- lr_scheduler_warmup_steps: 500
|
51 |
+
- training_steps: 10000
|
52 |
- mixed_precision_training: Native AMP
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
57 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
58 |
+
| 0.4091 | 1.68 | 1000 | 0.3728 |
|
59 |
+
| 0.3906 | 3.35 | 2000 | 0.3598 |
|
60 |
+
| 0.3899 | 5.03 | 3000 | 0.3543 |
|
61 |
+
| 0.3842 | 6.71 | 4000 | 0.3518 |
|
62 |
+
| 0.376 | 8.38 | 5000 | 0.3492 |
|
63 |
+
| 0.3745 | 10.06 | 6000 | 0.3474 |
|
64 |
+
| 0.3773 | 11.74 | 7000 | 0.3473 |
|
65 |
+
| 0.3774 | 13.41 | 8000 | 0.3461 |
|
66 |
+
| 0.3719 | 15.09 | 9000 | 0.3454 |
|
67 |
+
| 0.3712 | 16.76 | 10000 | 0.3452 |
|
68 |
|
69 |
|
70 |
### Framework versions
|