Commit
•
d56bd17
1
Parent(s):
53694a6
End of training
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the TTS_English_Technical_data dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
-
- Loss: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -54,16 +54,16 @@ The following hyperparameters were used during training:
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
-
| 4.
|
| 58 |
-
| 4.
|
| 59 |
-
| 4.
|
| 60 |
-
|
|
| 61 |
-
| 3.
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
| 65 |
|
| 66 |
- Transformers 4.46.0.dev0
|
| 67 |
- Pytorch 2.4.1+cu121
|
| 68 |
-
- Datasets 3.0.
|
| 69 |
- Tokenizers 0.20.1
|
|
|
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the TTS_English_Technical_data dataset.
|
| 21 |
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.4553
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 54 |
|
| 55 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
|:-------------:|:------:|:----:|:---------------:|
|
| 57 |
+
| 4.6344 | 0.3581 | 100 | 0.5150 |
|
| 58 |
+
| 4.3668 | 0.7162 | 200 | 0.4898 |
|
| 59 |
+
| 4.1304 | 1.0743 | 300 | 0.4713 |
|
| 60 |
+
| 3.9843 | 1.4324 | 400 | 0.4600 |
|
| 61 |
+
| 3.9375 | 1.7905 | 500 | 0.4553 |
|
| 62 |
|
| 63 |
|
| 64 |
### Framework versions
|
| 65 |
|
| 66 |
- Transformers 4.46.0.dev0
|
| 67 |
- Pytorch 2.4.1+cu121
|
| 68 |
+
- Datasets 3.0.2
|
| 69 |
- Tokenizers 0.20.1
|