End of training
Browse files
README.md
CHANGED
|
@@ -1,14 +1,11 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
-
base_model:
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
- name: speecht5_finetuned_emirhan_tr
|
| 8 |
results: []
|
| 9 |
-
pipeline_tag: text-to-speech
|
| 10 |
-
datasets:
|
| 11 |
-
- erenfazlioglu/turkishvoicedataset
|
| 12 |
---
|
| 13 |
|
| 14 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -16,9 +13,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# speecht5_finetuned_emirhan_tr
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -46,16 +43,18 @@ The following hyperparameters were used during training:
|
|
| 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:
|
| 50 |
- mixed_precision_training: Native AMP
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 55 |
|:-------------:|:------:|:----:|:---------------:|
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|
|
@@ -63,4 +62,4 @@ The following hyperparameters were used during training:
|
|
| 63 |
- Transformers 4.42.4
|
| 64 |
- Pytorch 2.4.0+cu121
|
| 65 |
- Datasets 2.21.0
|
| 66 |
-
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
base_model: microsoft/speecht5_tts
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
- name: speecht5_finetuned_emirhan_tr
|
| 8 |
results: []
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 13 |
|
| 14 |
# speecht5_finetuned_emirhan_tr
|
| 15 |
|
| 16 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
|
| 17 |
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.3234
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
- lr_scheduler_type: linear
|
| 45 |
- lr_scheduler_warmup_steps: 100
|
| 46 |
+
- training_steps: 500
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
| 49 |
### Training results
|
| 50 |
|
| 51 |
| Training Loss | Epoch | Step | Validation Loss |
|
| 52 |
|:-------------:|:------:|:----:|:---------------:|
|
| 53 |
+
| 0.5107 | 0.4545 | 100 | 0.4258 |
|
| 54 |
+
| 0.4183 | 0.9091 | 200 | 0.3814 |
|
| 55 |
+
| 0.3765 | 1.3636 | 300 | 0.3364 |
|
| 56 |
+
| 0.3562 | 1.8182 | 400 | 0.3308 |
|
| 57 |
+
| 0.3515 | 2.2727 | 500 | 0.3234 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 62 |
- Transformers 4.42.4
|
| 63 |
- Pytorch 2.4.0+cu121
|
| 64 |
- Datasets 2.21.0
|
| 65 |
+
- Tokenizers 0.19.1
|