Downloads · 30 days
72
8% of all-time downloads
speecht5_tts_commonvoice_en_03
Avitas8485/speecht5_tts_commonvoice_en_03
speecht5_tts_commonvoice_en_03 is a text-to-speech model from Avitas8485. 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
920
Public
Parameters
146M
1.8 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
- Jun 8, 2023
- Updated
- Sep 14, 2023
- SHA
- f3efd2e8
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_commonvoice_en_02
This model is a fine-tuned version of Avitas8485/speecht5_tts_commonvoice_en on the ljspeech dataset. It achieves the following results on the evaluation set:
- Loss: 0.3842
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: 500
- training_steps: 2000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4218 | 1.36 | 1000 | 0.3906 |
| 0.4193 | 2.71 | 2000 | 0.3842 |
Framework versions
- Transformers 4.31.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Task
- Text-to-Speech
- Library
- transformers
- Type
- speecht5
- License
- mit
- Languages
- en
- Created
- Jun 8, 2023
- Updated
- Sep 14, 2023