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: 3.3474
- Wer: 1.0
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: 5e-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: 20
- training_steps: 0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| No log | 0.2 | 20 | 11.2889 | 1.0 |
| 15.8315 | 0.4 | 40 | 3.3474 | 1.0 |
| 3.4511 | 0.6 | 60 | 3.1646 | 1.0 |
| 3.4511 | 0.8 | 80 | 3.1071 | 1.0 |
| 3.1703 | 1.0 | 100 | 3.0801 | 1.0 |
| 3.1056 | 1.2 | 120 | 3.0708 | 1.0 |
| 3.1056 | 1.4 | 140 | 3.0602 | 1.0 |
| 3.0782 | 1.6 | 160 | 3.0469 | 1.0 |
| 3.0491 | 1.8 | 180 | 3.0536 | 1.0 |
| 3.0491 | 2.0 | 200 | 3.0506 | 1.0 |
| 3.262 | 2.2 | 220 | 3.0482 | 1.0 |
| 3.0506 | 2.4 | 240 | 3.0418 | 1.0 |
| 3.0506 | 2.6 | 260 | 3.0357 | 1.0 |
| 3.1029 | 2.8 | 280 | 3.0308 | 1.0 |
| 3.0059 | 3.0 | 300 | 3.0351 | 1.0 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.3.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.2