metadata
license: apache-2.0
base_model: Strange18/wav2vec2-nepali-asr
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-nepali-asr
results: []
wav2vec2-nepali-asr
This model is a fine-tuned version of Strange18/wav2vec2-nepali-asr on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3957
- Wer: 0.3705
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: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.7578 | 1.5464 | 75 | 0.5105 | 0.4879 |
| 0.6844 | 3.0928 | 150 | 0.4736 | 0.4575 |
| 0.6367 | 4.6392 | 225 | 0.4586 | 0.4291 |
| 0.5977 | 6.1856 | 300 | 0.4387 | 0.4170 |
| 0.5714 | 7.7320 | 375 | 0.4350 | 0.4170 |
| 0.5815 | 9.2784 | 450 | 0.4255 | 0.4109 |
| 0.5629 | 10.8247 | 525 | 0.4260 | 0.4049 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1