dirichletian's picture
End of training
516faa2
---
language:
- nl
license: mit
base_model: microsoft/speecht5_tts
tags:
- tags
- generated_from_trainer
datasets:
- amharic_parallel
model-index:
- name: SpeechT5-TTS-Amh
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-TTS-Amh
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the alefa_asr dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3722
## 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: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- 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 |
|:-------------:|:-----:|:----:|:---------------:|
| 0.4268 | 3.46 | 1000 | 0.3934 |
| 0.4066 | 6.92 | 2000 | 0.3832 |
| 0.3997 | 10.38 | 3000 | 0.3745 |
| 0.3976 | 13.84 | 4000 | 0.3722 |
### Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3