metadata
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: ft-wav2vec2-with-minds-asr
results: []
ft-wav2vec2-with-minds-asr
This model is a fine-tuned version of facebook/wav2vec2-base on the PolyAI/minds14 dataset. It achieves the following results on the evaluation set:
- Loss: 14.6779
- Wer: 0.9992
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40
- training_steps: 80
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.2 | 20 | 18.3455 | 1.0 |
| 22.3132 | 0.4 | 40 | 14.6779 | 0.9992 |
| 12.9314 | 0.6 | 60 | 5.6604 | 1.0 |
| 12.9314 | 0.8 | 80 | 3.8006 | 1.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.3.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.2