JBZhang2342
commited on
Commit
•
9c7d2e2
1
Parent(s):
8054ced
Model save
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ base_model: microsoft/speecht5_tts
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
-
|
8 |
model-index:
|
9 |
- name: speecht5_tts
|
10 |
results: []
|
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# speecht5_tts
|
17 |
|
18 |
-
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -37,25 +37,21 @@ More information needed
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 1e-05
|
40 |
-
- train_batch_size:
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
43 |
- gradient_accumulation_steps: 2
|
44 |
-
- total_train_batch_size:
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
-
|
48 |
-
- training_steps: 4000
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch
|
54 |
-
|
55 |
-
| 0.
|
56 |
-
| 0.1781 | 2000.0 | 2000 | 0.6907 |
|
57 |
-
| 0.1697 | 3000.0 | 3000 | 0.7122 |
|
58 |
-
| 0.1699 | 4000.0 | 4000 | 0.7094 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- common_voice_1_0
|
8 |
model-index:
|
9 |
- name: speecht5_tts
|
10 |
results: []
|
|
|
15 |
|
16 |
# speecht5_tts
|
17 |
|
18 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_1_0 dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.7290
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
- learning_rate: 1e-05
|
40 |
+
- train_batch_size: 8
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
43 |
- gradient_accumulation_steps: 2
|
44 |
+
- total_train_batch_size: 16
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- training_steps: 100
|
|
|
48 |
- mixed_precision_training: Native AMP
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
54 |
+
| 0.7528 | 0.8 | 100 | 0.7290 |
|
|
|
|
|
|
|
55 |
|
56 |
|
57 |
### Framework versions
|