|
|
--- |
|
|
license: mit |
|
|
base_model: microsoft/speecht5_tts |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
model-index: |
|
|
- name: malay_checkpoint |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# malay_checkpoint |
|
|
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3983 |
|
|
|
|
|
## Model description |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Intended uses & limitations |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training and evaluation data |
|
|
|
|
|
More information needed |
|
|
|
|
|
## Training procedure |
|
|
|
|
|
### Training hyperparameters |
|
|
|
|
|
The following hyperparameters were used during training: |
|
|
- learning_rate: 1e-05 |
|
|
- train_batch_size: 16 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 2 |
|
|
- total_train_batch_size: 32 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 500 |
|
|
- training_steps: 8000 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 0.6478 | 0.21 | 500 | 0.5501 | |
|
|
| 0.5541 | 0.42 | 1000 | 0.4814 | |
|
|
| 0.5146 | 0.63 | 1500 | 0.4553 | |
|
|
| 0.4821 | 0.84 | 2000 | 0.4413 | |
|
|
| 0.4819 | 1.05 | 2500 | 0.4312 | |
|
|
| 0.4574 | 1.26 | 3000 | 0.4236 | |
|
|
| 0.4579 | 1.47 | 3500 | 0.4187 | |
|
|
| 0.443 | 1.68 | 4000 | 0.4156 | |
|
|
| 0.4525 | 1.88 | 4500 | 0.4095 | |
|
|
| 0.4736 | 2.09 | 5000 | 0.4054 | |
|
|
| 0.4486 | 2.3 | 5500 | 0.4045 | |
|
|
| 0.4471 | 2.51 | 6000 | 0.4017 | |
|
|
| 0.4436 | 2.72 | 6500 | 0.4012 | |
|
|
| 0.456 | 2.93 | 7000 | 0.4000 | |
|
|
| 0.432 | 3.14 | 7500 | 0.3991 | |
|
|
| 0.4239 | 3.35 | 8000 | 0.3983 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.40.0.dev0 |
|
|
- Pytorch 2.2.1+cu121 |
|
|
- Datasets 2.18.0 |
|
|
- Tokenizers 0.15.2 |
|
|
|
