metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_wolof_text_speech_1
results: []
speecht5_finetuned_wolof_text_speech_1
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: 0.3067
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: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3436 | 10.6809 | 1000 | 0.3205 |
| 0.3259 | 21.3618 | 2000 | 0.3155 |
| 0.3132 | 32.0427 | 3000 | 0.3102 |
| 0.3064 | 42.7236 | 4000 | 0.3078 |
| 0.2966 | 53.4045 | 5000 | 0.3080 |
| 0.2966 | 64.0854 | 6000 | 0.3072 |
| 0.2915 | 74.7664 | 7000 | 0.3066 |
| 0.2868 | 85.4473 | 8000 | 0.3081 |
| 0.2864 | 96.1282 | 9000 | 0.3066 |
| 0.2867 | 106.8091 | 10000 | 0.3067 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.4.0
- Datasets 3.0.1
- Tokenizers 0.20.0