Downloads · 30 days
5
9% of all-time downloads
Mehdi_Assamese_tts
kingmhd1519/Mehdi_Assamese_tts
Mehdi_Assamese_tts is a text-to-audio model from kingmhd1519. 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
56
Public
Parameters
144M
28.3 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
- Dec 21, 2024
- Updated
- Dec 21, 2024
- SHA
- 1ac462fe
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. -->
MEHDI_Assamese_TTS
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: 0.5555
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: 0.0002
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use 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: 200
- num_epochs: 155
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.2762 | 3.4561 | 100 | 0.5795 |
| 1.1771 | 6.9123 | 200 | 0.5489 |
| 1.1979 | 10.3509 | 300 | 0.5573 |
| 1.1083 | 13.8070 | 400 | 0.5319 |
| 1.0821 | 17.2456 | 500 | 0.5273 |
| 1.0297 | 20.7018 | 600 | 0.5075 |
| 1.0778 | 24.1404 | 700 | 0.5064 |
| 0.9818 | 27.5965 | 800 | 0.5098 |
| 0.9574 | 31.0351 | 900 | 0.4986 |
| 0.9571 | 34.4912 | 1000 | 0.5123 |
| 0.9955 | 37.9474 | 1100 | 0.5217 |
| 0.9455 | 41.3860 | 1200 | 0.5223 |
| 0.9084 | 44.8421 | 1300 | 0.5150 |
| 0.9057 | 48.2807 | 1400 | 0.5073 |
| 0.9038 | 51.7368 | 1500 | 0.5103 |
| 0.8802 | 55.1754 | 1600 | 0.5163 |
| 0.9033 | 58.6316 | 1700 | 0.5058 |
| 0.8507 | 62.0702 | 1800 | 0.5098 |
| 0.8549 | 65.5263 | 1900 | 0.5170 |
| 0.8795 | 68.9825 | 2000 | 0.5167 |
| 0.8629 | 72.4211 | 2100 | 0.5306 |
| 0.8577 | 75.8772 | 2200 | 0.5180 |
| 0.8197 | 79.3158 | 2300 | 0.5187 |
| 0.8278 | 82.7719 | 2400 | 0.5213 |
| 0.8016 | 86.2105 | 2500 | 0.5169 |
| 0.7927 | 89.6667 | 2600 | 0.5281 |
| 0.7815 | 93.1053 | 2700 | 0.5287 |
| 0.778 | 96.5614 | 2800 | 0.5288 |
| 0.7894 | 100.0 | 2900 | 0.5326 |
| 0.7521 | 103.4561 | 3000 | 0.5343 |
| 0.7705 | 106.9123 | 3100 | 0.5371 |
| 0.7652 | 110.3509 | 3200 | 0.5344 |
| 0.7458 | 113.8070 | 3300 | 0.5359 |
| 0.7583 | 117.2456 | 3400 | 0.5407 |
| 0.7479 | 120.7018 | 3500 | 0.5369 |
| 0.7338 | 124.1404 | 3600 | 0.5512 |
| 0.7662 | 127.5965 | 3700 | 0.5460 |
| 0.7212 | 131.0351 | 3800 | 0.5484 |
| 0.736 | 134.4912 | 3900 | 0.5447 |
| 0.7367 | 137.9474 | 4000 | 0.5536 |
| 0.7065 | 141.3860 | 4100 | 0.5566 |
| 0.711 | 144.8421 | 4200 | 0.5550 |
| 0.718 | 148.2807 | 4300 | 0.5555 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Dec 21, 2024
- Updated
- Dec 21, 2024