ManuD/tts_test_model
Browse files- README.md +11 -9
- generation_config.json +9 -0
README.md
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
---
|
2 |
license: mit
|
|
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
datasets:
|
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -45,20 +46,21 @@ The following hyperparameters were used during training:
|
|
45 |
- lr_scheduler_type: linear
|
46 |
- lr_scheduler_warmup_steps: 500
|
47 |
- training_steps: 4000
|
|
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
|
58 |
|
59 |
### Framework versions
|
60 |
|
61 |
-
- Transformers 4.
|
62 |
-
- Pytorch 2.
|
63 |
-
- Datasets 2.
|
64 |
-
- Tokenizers 0.
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: microsoft/speecht5_tts
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4596
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
46 |
- lr_scheduler_type: linear
|
47 |
- lr_scheduler_warmup_steps: 500
|
48 |
- training_steps: 4000
|
49 |
+
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 0.5221 | 2.77 | 1000 | 0.4784 |
|
56 |
+
| 0.506 | 5.53 | 2000 | 0.4662 |
|
57 |
+
| 0.495 | 8.3 | 3000 | 0.4613 |
|
58 |
+
| 0.4977 | 11.06 | 4000 | 0.4596 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
62 |
|
63 |
+
- Transformers 4.38.2
|
64 |
+
- Pytorch 2.2.1+cu121
|
65 |
+
- Datasets 2.18.0
|
66 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"max_length": 1876,
|
7 |
+
"pad_token_id": 1,
|
8 |
+
"transformers_version": "4.38.2"
|
9 |
+
}
|