# Load model directly
from transformers import AutoProcessor, AutoModelForTextToSpectrogram
processor = AutoProcessor.from_pretrained("AdanLee/speecht5_finetuned_voxpopuli_nl")
model = AutoModelForTextToSpectrogram.from_pretrained("AdanLee/speecht5_finetuned_voxpopuli_nl", device_map="auto")Quick Links
speecht5_finetuned_voxpopuli_nl
This model is a fine-tuned version of microsoft/speecht5_tts on the facebook/voxpopuli nl subset dataset. It achieves the following results on the evaluation set:
- Loss: 0.4725
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5348 | 4.04 | 500 | 0.4926 |
| 0.5155 | 9.02 | 1000 | 0.4783 |
| 0.5091 | 14.0 | 1500 | 0.4747 |
| 0.5004 | 18.04 | 2000 | 0.4725 |
Framework versions
- Transformers 4.32.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3
- Downloads last month
- 80
Model tree for AdanLee/speecht5_finetuned_voxpopuli_nl
Base model
microsoft/speecht5_tts
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="AdanLee/speecht5_finetuned_voxpopuli_nl")