metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_jenny_2000sample
results: []
speecht5_jenny_2000sample
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3933
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: 3e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5538 | 0.4444 | 50 | 0.4639 |
| 0.507 | 0.8889 | 100 | 0.4439 |
| 0.4823 | 1.3333 | 150 | 0.4217 |
| 0.4739 | 1.7778 | 200 | 0.4156 |
| 0.4661 | 2.2222 | 250 | 0.4094 |
| 0.4582 | 2.6667 | 300 | 0.4071 |
| 0.439 | 3.1111 | 350 | 0.4024 |
| 0.4499 | 3.5556 | 400 | 0.4038 |
| 0.4379 | 4.0 | 450 | 0.4004 |
| 0.4294 | 4.4444 | 500 | 0.3995 |
| 0.427 | 4.8889 | 550 | 0.3963 |
| 0.4262 | 5.3333 | 600 | 0.3957 |
| 0.4319 | 5.7778 | 650 | 0.3959 |
| 0.4171 | 6.2222 | 700 | 0.3948 |
| 0.4248 | 6.6667 | 750 | 0.3967 |
| 0.4195 | 7.1111 | 800 | 0.3946 |
| 0.4174 | 7.5556 | 850 | 0.3939 |
| 0.4183 | 8.0 | 900 | 0.3945 |
| 0.4107 | 8.4444 | 950 | 0.3934 |
| 0.422 | 8.8889 | 1000 | 0.3933 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1