Downloads · 30 days
9
12% of all-time downloads
Bangla-tts-small
tahmidkhanalim/Bangla-tts-small
Bangla-tts-small is a text-to-audio model from tahmidkhanalim. 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
76
Public
Parameters
144M
11.6 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
- Apr 9, 2025
- Updated
- Apr 9, 2025
- SHA
- 20e5c3f6
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. -->
Bangla-tts-small
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4127
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 1500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.33 | 99.6154 | 100 | 0.3955 |
| 0.3199 | 199.6154 | 200 | 0.4201 |
| 0.3083 | 299.6154 | 300 | 0.3931 |
| 0.2953 | 399.6154 | 400 | 0.3909 |
| 0.2892 | 499.6154 | 500 | 0.4071 |
| 0.2813 | 599.6154 | 600 | 0.3986 |
| 0.2789 | 699.6154 | 700 | 0.4070 |
| 0.2661 | 799.6154 | 800 | 0.4091 |
| 0.2605 | 899.6154 | 900 | 0.4065 |
| 0.2586 | 999.6154 | 1000 | 0.4291 |
| 0.2549 | 1099.6154 | 1100 | 0.4386 |
| 0.253 | 1199.6154 | 1200 | 0.4261 |
| 0.2492 | 1299.6154 | 1300 | 0.4205 |
| 0.2519 | 1399.6154 | 1400 | 0.4168 |
| 0.2473 | 1499.6154 | 1500 | 0.4127 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Apr 9, 2025
- Updated
- Apr 9, 2025