End of training
Browse files
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# Sindhi-TTS
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [fahadqazi/Sindhi-TTS](https://huggingface.co/fahadqazi/Sindhi-TTS) on the None dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
@@ -33,7 +35,7 @@ More information needed
|
|
| 33 |
### Training hyperparameters
|
| 34 |
|
| 35 |
The following hyperparameters were used during training:
|
| 36 |
-
- learning_rate:
|
| 37 |
- train_batch_size: 8
|
| 38 |
- eval_batch_size: 2
|
| 39 |
- seed: 42
|
|
@@ -42,9 +44,25 @@ The following hyperparameters were used during training:
|
|
| 42 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 43 |
- lr_scheduler_type: linear
|
| 44 |
- lr_scheduler_warmup_steps: 100
|
| 45 |
-
- training_steps:
|
| 46 |
- mixed_precision_training: Native AMP
|
| 47 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
### Framework versions
|
| 49 |
|
| 50 |
- Transformers 4.46.2
|
|
|
|
| 15 |
# Sindhi-TTS
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [fahadqazi/Sindhi-TTS](https://huggingface.co/fahadqazi/Sindhi-TTS) on the None dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.2937
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 35 |
### Training hyperparameters
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 7e-05
|
| 39 |
- train_batch_size: 8
|
| 40 |
- eval_batch_size: 2
|
| 41 |
- seed: 42
|
|
|
|
| 44 |
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
- lr_scheduler_type: linear
|
| 46 |
- lr_scheduler_warmup_steps: 100
|
| 47 |
+
- training_steps: 1000
|
| 48 |
- mixed_precision_training: Native AMP
|
| 49 |
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:-------:|:----:|:---------------:|
|
| 54 |
+
| 0.3182 | 2.5409 | 100 | 0.3032 |
|
| 55 |
+
| 0.3142 | 5.0943 | 200 | 0.3041 |
|
| 56 |
+
| 0.3171 | 7.6352 | 300 | 0.3021 |
|
| 57 |
+
| 0.3132 | 10.1887 | 400 | 0.2994 |
|
| 58 |
+
| 0.3105 | 12.7296 | 500 | 0.2982 |
|
| 59 |
+
| 0.3084 | 15.2830 | 600 | 0.2971 |
|
| 60 |
+
| 0.3081 | 17.8239 | 700 | 0.2973 |
|
| 61 |
+
| 0.3085 | 20.3774 | 800 | 0.2954 |
|
| 62 |
+
| 0.3033 | 22.9182 | 900 | 0.2943 |
|
| 63 |
+
| 0.3079 | 25.4717 | 1000 | 0.2937 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
### Framework versions
|
| 67 |
|
| 68 |
- Transformers 4.46.2
|