metadata
language:
- ckb
license: mit
tags:
- hf-tts-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
model-index:
- name: SpeechT5 tts ckb7- Saber Molaei
results: []
pipeline_tag: text-to-speech
SpeechT5 tts ckb7- Saber Molaei
This model is a fine-tuned version of microsoft/speecht5_tts on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5043
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: 4
- 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: 7000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6297 | 2.93 | 1000 | 0.5741 |
| 0.5784 | 5.85 | 2000 | 0.5376 |
| 0.5576 | 8.78 | 3000 | 0.5230 |
| 0.5563 | 11.7 | 4000 | 0.5120 |
| 0.5257 | 14.63 | 5000 | 0.5070 |
| 0.5375 | 17.56 | 6000 | 0.5028 |
| 0.5365 | 20.48 | 7000 | 0.5043 |
Framework versions
- Transformers 4.30.0.dev0
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3