metadata
base_model: facebook/wav2vec2-base
license: apache-2.0
metrics:
- wer
tags:
- generated_from_trainer
model-index:
- name: 240615-wav2vec2-ASR-English
results: []
240615-wav2vec2-ASR-English
This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9291
- Wer: 0.1578
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: 5
- 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
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 6.25 | 100 | 0.8718 | 0.1610 |
| No log | 12.5 | 200 | 0.9291 | 0.1578 |
| No log | 18.75 | 300 | 0.8387 | 0.1755 |
| No log | 25.0 | 400 | 0.8754 | 0.1675 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1