metadata
license: mit
base_model: jaymanvirk/speecht5_tts_finetuned_voxpopuli_lt
tags:
- generated_from_trainer
datasets:
- voxpopuli
model-index:
- name: speecht5_tts_finetuned_voxpopuli_lt
results: []
speecht5_tts_finetuned_voxpopuli_lt
This model is a fine-tuned version of jaymanvirk/speecht5_tts_finetuned_voxpopuli_lt on the voxpopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.4718
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: 5e-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: 50
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.5879 | 3.06 | 100 | 0.5127 |
0.5239 | 7.04 | 200 | 0.4850 |
0.4996 | 11.04 | 300 | 0.4766 |
0.4897 | 15.03 | 400 | 0.4718 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.15.2