|
---
|
|
library_name: transformers
|
|
license: mit
|
|
base_model: microsoft/speecht5_tts
|
|
tags:
|
|
- generated_from_trainer
|
|
model-index:
|
|
- name: speecht5_finetuned_ruslan
|
|
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_finetuned_ruslan
|
|
|
|
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: 0.6032
|
|
|
|
## 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
- lr_scheduler_type: linear
|
|
- lr_scheduler_warmup_steps: 500
|
|
- training_steps: 4000
|
|
- mixed_precision_training: Native AMP
|
|
|
|
### Training results
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss |
|
|
|:-------------:|:------:|:----:|:---------------:|
|
|
| 0.7792 | 1.8373 | 1000 | 0.7524 |
|
|
| 0.712 | 3.6757 | 2000 | 0.6561 |
|
|
| 0.6672 | 5.5141 | 3000 | 0.6223 |
|
|
| 0.6539 | 7.3525 | 4000 | 0.6032 |
|
|
|
|
|
|
### Framework versions
|
|
|
|
- Transformers 4.47.0.dev0
|
|
- Pytorch 2.2.1+cu118
|
|
- Datasets 2.18.0
|
|
- Tokenizers 0.20.3
|
|
|
