Update README.md
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 CML-TTS dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -53,12 +53,19 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
-
| Training Loss |
|
| 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 CML-TTS dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.413100
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
+
| Training Loss | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:----:|:---------------:|
|
| 58 |
+
| 0.571400 | 250 | 0.513316 |
|
| 59 |
+
| 0.475900 | 500 | 0.436505 |
|
| 60 |
+
| 0.459000 | 750 | 0.422115 |
|
| 61 |
+
| 0.446800 | 1000 | 0.412104 |
|
| 62 |
+
| 0.439400 | 1250 | 0.403607 |
|
| 63 |
+
| 0.438600 | 1500 | 0.400913 |
|
| 64 |
+
| 0.437600 | 1750 | 0.398770 |
|
| 65 |
+
| 0.420900 | 2000 | 0.395658 |
|
| 66 |
+
| 0.427000 | 2250 | 0.393763 |
|
| 67 |
+
| 0.428000 | 2500 | 0.392377 |
|
| 68 |
+
| 0.425100 | 2750 | 0.392968 |
|
| 69 |
|
| 70 |
|
| 71 |
### Framework versions
|