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: 0.5845
- Wer: 18.9294
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: 12
- eval_batch_size: 12
- 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: 10000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.2138 | 0.96 | 2000 | 0.4851 | 20.9147 |
| 0.1005 | 1.93 | 4000 | 0.5006 | 20.7187 |
| 0.029 | 2.89 | 6000 | 0.5342 | 19.6702 |
| 0.0092 | 3.85 | 8000 | 0.5682 | 19.0752 |
| 0.0029 | 4.82 | 10000 | 0.5845 | 18.9294 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0