|
--- |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice_13_0 |
|
model-index: |
|
- name: 01-08-2023_19-25-49 |
|
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. --> |
|
|
|
# 01-08-2023_19-25-49 |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_13_0 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5452 |
|
|
|
## 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: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- training_steps: 6000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.5581 | 1.0 | 884 | 0.6011 | |
|
| 0.5129 | 2.0 | 1768 | 0.5674 | |
|
| 0.5038 | 3.0 | 2652 | 0.5604 | |
|
| 0.5068 | 4.0 | 3536 | 0.5502 | |
|
| 0.4936 | 5.0 | 4420 | 0.5465 | |
|
| 0.4871 | 6.0 | 5304 | 0.5426 | |
|
| 0.4855 | 6.79 | 6000 | 0.5452 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.0.dev0 |
|
- Pytorch 1.10.1+cu113 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|