Downloads · 30 days
11
2% of all-time downloads
mabama-tts-es
ovieyra21/mabama-tts-es
mabama-tts-es is a text-to-speech model from ovieyra21. 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
575
Public
Parameters
146M
1.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin585 MB · 50%
At a glance
- Task
- Text-to-Speech
- Library
- transformers
- License
- mit
- Model type
- speecht5
- Access
- Public
- Created
- Mar 26, 2024
- Updated
- Aug 12, 2024
- SHA
- 5a06e210
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. -->
mabama-tts-v1
This model is a fine-tuned version of microsoft/speecht5_tts on the mabama-v4 dataset.
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: 500
- training_steps: 4000
- mixed_precision_training: Native AMP
Framework versions
- Transformers 4.28.0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.13.3 Download them in the Files & versions tab.
- Task
- Text-to-Speech
- Library
- transformers
- Type
- speecht5
- License
- mit
- Languages
- es
- Created
- Mar 26, 2024
- Updated
- Aug 12, 2024