metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_improved_data_wo_knn
results: []
speecht5_improved_data_wo_knn
This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5957
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: 8
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 3000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9419 | 0.8097 | 250 | 0.8022 |
| 0.7827 | 1.6194 | 500 | 0.6917 |
| 0.7165 | 2.4291 | 750 | 0.6538 |
| 0.7038 | 3.2389 | 1000 | 0.6365 |
| 0.6821 | 4.0486 | 1250 | 0.6194 |
| 0.685 | 4.8583 | 1500 | 0.6156 |
| 0.6608 | 5.6680 | 1750 | 0.6083 |
| 0.6725 | 6.4777 | 2000 | 0.6051 |
| 0.6592 | 7.2874 | 2250 | 0.6009 |
| 0.6617 | 8.0972 | 2500 | 0.5981 |
| 0.6565 | 8.9069 | 2750 | 0.5962 |
| 0.6536 | 9.7166 | 3000 | 0.5957 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.1.2
- Datasets 2.17.0
- Tokenizers 0.19.1