|
--- |
|
language: |
|
- en |
|
license: mit |
|
base_model: Avitas8485/speecht5_tts_commonvoice_en_05 |
|
tags: |
|
- text-to-speech |
|
- generated_from_trainer |
|
datasets: |
|
- lj_speech |
|
model-index: |
|
- name: speecht5_tts_commonvoice_en_06 |
|
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. --> |
|
|
|
# speecht5_tts_commonvoice_en_06 |
|
|
|
This model is a fine-tuned version of [Avitas8485/speecht5_tts_commonvoice_en_05](https://huggingface.co/Avitas8485/speecht5_tts_commonvoice_en_05) on the ljspeech dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3607 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- training_steps: 8000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.4009 | 1.36 | 1000 | 0.3658 | |
|
| 0.3939 | 2.71 | 2000 | 0.3648 | |
|
| 0.3976 | 4.07 | 3000 | 0.3635 | |
|
| 0.3975 | 5.43 | 4000 | 0.3624 | |
|
| 0.3878 | 6.78 | 5000 | 0.3613 | |
|
| 0.3956 | 8.14 | 6000 | 0.3612 | |
|
| 0.3947 | 9.5 | 7000 | 0.3608 | |
|
| 0.3854 | 10.85 | 8000 | 0.3607 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0.dev0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
