Downloads · 30 days
6
3% of all-time downloads
speecht5_finetuned_voxpopuli_sk
CodingQueen13/speecht5_finetuned_voxpopuli_sk
speecht5_finetuned_voxpopuli_sk is a text-to-speech model from CodingQueen13. Use it when you need text read aloud. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
172
Public
Parameters
144M
2.3 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors578 MB · 100%
At a glance
- Task
- Text-to-Speech
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Aug 27, 2024
- Updated
- Aug 28, 2024
- SHA
- 49fcb4fc
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_finetuned_voxpopuli_nl
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: 0.4361
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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4903 | 10.2828 | 1000 | 0.4498 |
| 0.4637 | 20.5656 | 2000 | 0.4383 |
| 0.4591 | 30.8483 | 3000 | 0.4364 |
| 0.4621 | 41.1311 | 4000 | 0.4361 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1
- Task
- Text-to-Speech
- Type
- speecht5
- License
- mit
- Created
- Aug 27, 2024
- Updated
- Aug 28, 2024