metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- audiofolder
model-index:
- name: stt-audioPt-bambara-french_25
results: []
stt-audioPt-bambara-french_25
This model is a fine-tuned version of microsoft/speecht5_tts on the audiofolder dataset. It achieves the following results on the evaluation set:
- Loss: 0.5058
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: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9044 | 66.6780 | 1000 | 0.5086 |
| 3.297 | 133.3390 | 2000 | 0.4898 |
| 3.1553 | 200.0 | 3000 | 0.4952 |
| 3.0935 | 266.6780 | 4000 | 0.4970 |
| 2.9243 | 333.3390 | 5000 | 0.5058 |
Framework versions
- Transformers 4.48.0.dev0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0