Text-to-Audio
Transformers
TensorBoard
Safetensors
Guianese Creole French
speecht5
Generated from Trainer
# Load model directly
from transformers import AutoProcessor, AutoModelForTextToSpectrogram
processor = AutoProcessor.from_pretrained("EvgenyShivchenkoUIT/speecht5_finetuned_gcr_1")
model = AutoModelForTextToSpectrogram.from_pretrained("EvgenyShivchenkoUIT/speecht5_finetuned_gcr_1")Quick Links
TTS SpeechT5 GCR
This model is a fine-tuned version of EvgenyShivchenkoUIT/speecht5_fr on the GuianeseCreole dataset. It achieves the following results on the evaluation set:
- Loss: 0.4620
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: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- training_steps: 900
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6239 | 3.4622 | 100 | 0.5140 |
| 0.5214 | 6.9244 | 200 | 0.4837 |
| 0.4827 | 10.3556 | 300 | 0.4767 |
| 0.4799 | 13.8178 | 400 | 0.4722 |
| 0.4624 | 17.2489 | 500 | 0.4696 |
| 0.4609 | 20.7111 | 600 | 0.4659 |
| 0.4499 | 24.1422 | 700 | 0.4598 |
| 0.4488 | 27.6044 | 800 | 0.4599 |
| 0.4432 | 31.0356 | 900 | 0.4620 |
Framework versions
- Transformers 4.52.0
- Pytorch 2.11.0+cu128
- Datasets 3.6.0
- Tokenizers 0.21.4
- Downloads last month
- 5
Model tree for EvgenyShivchenkoUIT/speecht5_finetuned_gcr_1
Base model
microsoft/speecht5_tts Finetuned
EvgenyShivchenkoUIT/speecht5_fr
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="EvgenyShivchenkoUIT/speecht5_finetuned_gcr_1")