Downloads · 30 days
11
7% of all-time downloads
speecht5_tts_vi
BinhMinhs10/speecht5_tts_vi
speecht5_tts_vi is a text-to-speech model from BinhMinhs10. Use it when you need text read aloud. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
168
Public
Parameters
144M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors578 MB · 100%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- Model type
- speecht5
- Access
- Public
- Created
- May 10, 2024
- Updated
- May 10, 2024
- SHA
- c2b934d0
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 Vietnamese
This model is a fine-tuned version of truong-xuan-linh/speecht5-multilingual-voiceclone-speechbrain on the vivos dataset. It achieves the following results on the evaluation set:
- Loss: 0.3724
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4272 | 1.5244 | 500 | 0.3835 |
| 0.408 | 3.0488 | 1000 | 0.3724 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Task
- Text-to-Speech
- Library
- transformers
- Type
- speecht5
- Languages
- vi
- Created
- May 10, 2024
- Updated
- May 10, 2024