Downloads · 30 days
8
12% of all-time downloads
speecht5_finetuned_voxpopuli
Bunny2308/speecht5_finetuned_voxpopuli
speecht5_finetuned_voxpopuli is a text-to-audio model from Bunny2308. Use it for the text-to-audio task on the model card, and read the license before you ship it in a product. 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
66
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
- Task
- Text-to-Audio
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- 96dd02b8
Base models
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_finetuned_voxpopuli
This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4674
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: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 100
- training_steps: 2000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.1675 | 3.3361 | 50 | 0.4714 |
| 4.0389 | 6.6723 | 100 | 0.4676 |
| 3.9838 | 10.0 | 150 | 0.4698 |
| 3.9038 | 13.3361 | 200 | 0.4661 |
| 3.8934 | 16.6723 | 250 | 0.4644 |
| 3.8950 | 20.0 | 300 | 0.4624 |
| 3.8865 | 23.3361 | 350 | 0.4625 |
| 3.8657 | 26.6723 | 400 | 0.4623 |
| 3.7982 | 30.0 | 450 | 0.4601 |
| 3.8135 | 33.3361 | 500 | 0.4606 |
| 3.8142 | 36.6723 | 550 | 0.4589 |
| 3.7940 | 40.0 | 600 | 0.4643 |
| 3.7503 | 43.3361 | 650 | 0.4638 |
| 3.7784 | 46.6723 | 700 | 0.4613 |
| 3.7093 | 50.0 | 750 | 0.4602 |
| 3.7413 | 53.3361 | 800 | 0.4649 |
| 3.7262 | 56.6723 | 850 | 0.4592 |
| 3.7326 | 60.0 | 900 | 0.4630 |
| 3.7416 | 63.3361 | 950 | 0.4657 |
| 3.7067 | 66.6723 | 1000 | 0.4647 |
| 3.6877 | 70.0 | 1050 | 0.4679 |
| 3.6731 | 73.3361 | 1100 | 0.4633 |
| 3.7205 | 76.6723 | 1150 | 0.4658 |
| 3.6800 | 80.0 | 1200 | 0.4673 |
| 3.6686 | 83.3361 | 1250 | 0.4672 |
| 3.7000 | 86.6723 | 1300 | 0.4657 |
| 3.6402 | 90.0 | 1350 | 0.4658 |
| 3.6702 | 93.3361 | 1400 | 0.4651 |
| 3.6857 | 96.6723 | 1450 | 0.4649 |
| 3.6597 | 100.0 | 1500 | 0.4635 |
| 3.6371 | 103.3361 | 1550 | 0.4653 |
| 3.6502 | 106.6723 | 1600 | 0.4652 |
| 3.6590 | 110.0 | 1650 | 0.4656 |
| 3.6618 | 113.3361 | 1700 | 0.4654 |
| 3.6744 | 116.6723 | 1750 | 0.4671 |
| 3.6589 | 120.0 | 1800 | 0.4679 |
| 3.6300 | 123.3361 | 1850 | 0.4672 |
| 3.6503 | 126.6723 | 1900 | 0.4669 |
| 3.6394 | 130.0 | 1950 | 0.4653 |
| 3.6410 | 133.3361 | 2000 | 0.4674 |
Framework versions
- Transformers 5.17.0.dev0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.23.1
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026