|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: microsoft/speecht5_tts |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice_17_0 |
|
model-index: |
|
- name: Hindi_SpeechT5_finetuned |
|
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. --> |
|
|
|
# Hindi_SpeechT5_finetuned |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_17_0 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4484 |
|
|
|
## 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: 0.0001 |
|
- 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: 100 |
|
- training_steps: 1500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 0.6781 | 0.3442 | 100 | 0.5528 | |
|
| 0.5834 | 0.6885 | 200 | 0.5470 | |
|
| 0.554 | 1.0327 | 300 | 0.5090 | |
|
| 0.5397 | 1.3769 | 400 | 0.5025 | |
|
| 0.526 | 1.7212 | 500 | 0.4872 | |
|
| 0.5224 | 2.0654 | 600 | 0.4846 | |
|
| 0.515 | 2.4096 | 700 | 0.4754 | |
|
| 0.5047 | 2.7539 | 800 | 0.4703 | |
|
| 0.5014 | 3.0981 | 900 | 0.4689 | |
|
| 0.4946 | 3.4423 | 1000 | 0.4601 | |
|
| 0.4912 | 3.7866 | 1100 | 0.4584 | |
|
| 0.4847 | 4.1308 | 1200 | 0.4554 | |
|
| 0.4824 | 4.4750 | 1300 | 0.4514 | |
|
| 0.4831 | 4.8193 | 1400 | 0.4501 | |
|
| 0.4723 | 5.1635 | 1500 | 0.4484 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.44.2 |
|
- Pytorch 2.5.0+cu121 |
|
- Datasets 3.0.2 |
|
- Tokenizers 0.19.1 |
|
|
