Downloads · 30 days
3
5% of all-time downloads
v1
aryamannningombam/v1
v1 is a text-to-audio model from aryamannningombam. 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
60
Public
Parameters
144M
12.7 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
- Mar 7, 2024
- Updated
- Mar 7, 2024
- SHA
- 9677dadc
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. -->
v1
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: 0.4063
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 900
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4758 | 0.51 | 1000 | 0.4393 |
| 0.4714 | 1.02 | 2000 | 0.4303 |
| 0.4673 | 1.54 | 3000 | 0.4272 |
| 0.4646 | 2.05 | 4000 | 0.4206 |
| 0.4509 | 2.56 | 5000 | 0.4197 |
| 0.4542 | 3.07 | 6000 | 0.4162 |
| 0.4526 | 3.59 | 7000 | 0.4153 |
| 0.4484 | 4.1 | 8000 | 0.4134 |
| 0.4539 | 4.61 | 9000 | 0.4134 |
| 0.4467 | 5.12 | 10000 | 0.4111 |
| 0.4465 | 5.64 | 11000 | 0.4112 |
| 0.4424 | 6.15 | 12000 | 0.4091 |
| 0.4422 | 6.66 | 13000 | 0.4079 |
| 0.4532 | 7.17 | 14000 | 0.4084 |
| 0.447 | 7.69 | 15000 | 0.4074 |
| 0.4398 | 8.2 | 16000 | 0.4069 |
| 0.4386 | 8.71 | 17000 | 0.4068 |
| 0.4379 | 9.22 | 18000 | 0.4069 |
| 0.4345 | 9.74 | 19000 | 0.4063 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Text-to-Audio
- Library
- transformers
- Type
- speecht5
- License
- mit
- Created
- Mar 7, 2024
- Updated
- Mar 7, 2024