|
--- |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- facebook/voxpopuli |
|
model-index: |
|
- name: speecht5_quick_finetuned_voxpopuli_it |
|
results: [] |
|
pipeline_tag: text-to-speech |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# speecht5_quick_finetuned_voxpopuli_it |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4879 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- 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: 250 |
|
- training_steps: 2500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.5535 | 1.53 | 250 | 0.5129 | |
|
| 0.5395 | 3.07 | 500 | 0.5065 | |
|
| 0.5393 | 4.6 | 750 | 0.4994 | |
|
| 0.5316 | 6.13 | 1000 | 0.4956 | |
|
| 0.5372 | 7.66 | 1250 | 0.4919 | |
|
| 0.53 | 9.2 | 1500 | 0.4914 | |
|
| 0.5277 | 10.73 | 1750 | 0.4888 | |
|
| 0.5198 | 12.26 | 2000 | 0.4896 | |
|
| 0.5236 | 13.79 | 2250 | 0.4880 | |
|
| 0.5209 | 15.33 | 2500 | 0.4879 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
