metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
datasets:
- common_voice_17_0
model-index:
- name: Speect5-common-voice-Hindi
results: []
Speect5-common-voice-Hindi
This model is a fine-tuned version of microsoft/speecht5_tts on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4800
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 3.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6618 | 0.3445 | 100 | 0.6072 |
| 0.5936 | 0.6891 | 200 | 0.5618 |
| 0.5591 | 1.0336 | 300 | 0.5116 |
| 0.5412 | 1.3781 | 400 | 0.5120 |
| 0.5361 | 1.7227 | 500 | 0.4981 |
| 0.5272 | 2.0672 | 600 | 0.4922 |
| 0.5175 | 2.4117 | 700 | 0.4816 |
| 0.5179 | 2.7562 | 800 | 0.4800 |
Framework versions
- Transformers 4.46.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1