speecht5_tts_tandt / README.md
andre-coy's picture
End of training
9f48a6b
|
raw
history blame
1.6 kB
---
language:
- en
license: mit
base_model: microsoft/speecht5_tts
tags:
- Trinidadian TTS
- generated_from_trainer
datasets:
- MK_TandT
model-index:
- name: SpeechT5_Trini
results: []
---
<!-- 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_Trini
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the TandT dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3751
## 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
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4358 | 4.78 | 1000 | 0.3881 |
| 0.4205 | 9.57 | 2000 | 0.3799 |
| 0.4029 | 14.35 | 3000 | 0.3749 |
| 0.4106 | 19.14 | 4000 | 0.3751 |
### Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3