metadata
language:
- hi
license: apache-2.0
base_model: reproductionguru/voicetest6
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: base
results: []
base
This model is a fine-tuned version of reproductionguru/voicetest6 on the tutorial Voice 11.0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4757
- Wer: 21.0355
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.4953 | 0.4 | 1000 | 0.6332 | 30.4347 |
| 0.408 | 0.8 | 2000 | 0.5400 | 25.3584 |
| 0.2074 | 1.2 | 3000 | 0.5097 | 23.7629 |
| 0.1796 | 1.61 | 4000 | 0.4885 | 21.6339 |
| 0.1583 | 2.01 | 5000 | 0.4757 | 21.0355 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0