|
--- |
|
language: |
|
- as |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- google/fluers |
|
model-index: |
|
- name: SpeechT5 TTS Assamese |
|
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 Assamese |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co./microsoft/speecht5_tts) on the Google fluers dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3991 |
|
|
|
## 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: 0.0002 |
|
- 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: 200 |
|
- training_steps: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:--------:|:----:|:---------------:| |
|
| 0.4812 | 30.7692 | 200 | 0.4176 | |
|
| 0.4038 | 61.5385 | 400 | 0.4009 | |
|
| 0.3862 | 92.3077 | 600 | 0.3885 | |
|
| 0.3433 | 123.0769 | 800 | 0.3843 | |
|
| 0.3252 | 153.8462 | 1000 | 0.3991 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
|
|
