Downloads · 30 days
8
3% of all-time downloads
speecht5_tts_voxpopuli_nl_2
zongxiao/speecht5_tts_voxpopuli_nl_2
speecht5_tts_voxpopuli_nl_2 is a text-to-speech model from zongxiao. Use it when you need text read aloud. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
279
Public
Repo size
2.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin578 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Oct 7, 2023
- Updated
- Oct 7, 2023
- SHA
- 6a26f9a1
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 Dutch
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: 0.4491
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-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 500
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4883 | 2.15 | 500 | 0.4505 |
| 0.4856 | 4.3 | 1000 | 0.4503 |
| 0.4896 | 6.45 | 1500 | 0.4500 |
| 0.4912 | 8.6 | 2000 | 0.4491 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3
- Task
- Text-to-Speech
- Library
- transformers
- Type
- speecht5
- License
- mit
- Languages
- nl
- Created
- Oct 7, 2023
- Updated
- Oct 7, 2023