Downloads · 30 days
5
2% of all-time downloads
speecht5_tts_voxpopuli_de
sophiayk20/speecht5_tts_voxpopuli_de
speecht5_tts_voxpopuli_de is a machine learning model from sophiayk20. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
252
Public
Parameters
144M
2.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors578 MB · 100%
At a glance
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Aug 24, 2024
- Updated
- Aug 24, 2024
- SHA
- dde3af86
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
SpeechT5 TTS German
This model is a fine-tuned version of microsoft/speecht5_tts on the VoxPopuli dataset. It achieves the following results on the evaluation set:
- Loss: 0.4570
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: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5087 | 9.0293 | 1000 | 0.4735 |
| 0.4943 | 18.0587 | 2000 | 0.4615 |
| 0.4928 | 27.0880 | 3000 | 0.4585 |
| 0.485 | 36.1174 | 4000 | 0.4570 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Type
- speecht5
- License
- mit
- Languages
- de
- Created
- Aug 24, 2024
- Updated
- Aug 24, 2024