End of training
Browse files
README.md
CHANGED
|
@@ -18,12 +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 common_voice_13_0 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
-
|
| 22 |
-
- eval_runtime: 39.7853
|
| 23 |
-
- eval_samples_per_second: 22.496
|
| 24 |
-
- eval_steps_per_second: 11.26
|
| 25 |
-
- epoch: 11.1221
|
| 26 |
-
- step: 2800
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
|
@@ -51,12 +46,28 @@ The following hyperparameters were used during training:
|
|
| 51 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
- lr_scheduler_type: linear
|
| 53 |
- lr_scheduler_warmup_steps: 100
|
| 54 |
-
- training_steps:
|
| 55 |
- mixed_precision_training: Native AMP
|
| 56 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.44.2
|
| 60 |
-
- Pytorch
|
| 61 |
- Datasets 3.0.0
|
| 62 |
- Tokenizers 0.19.1
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_13_0 dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5641
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
- lr_scheduler_warmup_steps: 100
|
| 49 |
+
- training_steps: 1000
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
+
### Training results
|
| 53 |
+
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
+
| 0.7879 | 0.3972 | 100 | 0.6982 |
|
| 57 |
+
| 0.7078 | 0.7944 | 200 | 0.6603 |
|
| 58 |
+
| 0.6728 | 1.1917 | 300 | 0.6420 |
|
| 59 |
+
| 0.646 | 1.5889 | 400 | 0.5979 |
|
| 60 |
+
| 0.6276 | 1.9861 | 500 | 0.5954 |
|
| 61 |
+
| 0.6213 | 2.3833 | 600 | 0.5852 |
|
| 62 |
+
| 0.6161 | 2.7805 | 700 | 0.5805 |
|
| 63 |
+
| 0.6043 | 3.1778 | 800 | 0.5701 |
|
| 64 |
+
| 0.6012 | 3.5750 | 900 | 0.5624 |
|
| 65 |
+
| 0.5951 | 3.9722 | 1000 | 0.5641 |
|
| 66 |
+
|
| 67 |
+
|
| 68 |
### Framework versions
|
| 69 |
|
| 70 |
- Transformers 4.44.2
|
| 71 |
+
- Pytorch 2.3.0+cu118
|
| 72 |
- Datasets 3.0.0
|
| 73 |
- Tokenizers 0.19.1
|