|
--- |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Finetuned_speecht5 |
|
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. --> |
|
|
|
# Finetuned_speecht5 |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5028 |
|
|
|
## 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: 8 |
|
- 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: 5000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-------:|:----:|:---------------:| |
|
| 0.6106 | 8.8496 | 500 | 0.5241 | |
|
| 0.5243 | 17.6991 | 1000 | 0.4949 | |
|
| 0.5004 | 26.5487 | 1500 | 0.4873 | |
|
| 0.4918 | 35.3982 | 2000 | 0.4871 | |
|
| 0.4927 | 44.2478 | 2500 | 0.4922 | |
|
| 0.4715 | 53.0973 | 3000 | 0.4964 | |
|
| 0.4832 | 61.9469 | 3500 | 0.4996 | |
|
| 0.4744 | 70.7965 | 4000 | 0.5028 | |
|
| 0.4677 | 79.6460 | 4500 | 0.5046 | |
|
| 0.4568 | 88.4956 | 5000 | 0.5028 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.3 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
