---
license: apache-2.0
base_model: facebook/wav2vec2-base
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: ft-wav2vec2-with-minds-asr
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# ft-wav2vec2-with-minds-asr

This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the PolyAI/minds14 dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2186
- 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

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:---:|
| No log        | 0.2   | 20   | 3.7561          | 1.0 |
| 8.7776        | 0.4   | 40   | 3.2186          | 1.0 |
| 3.2979        | 0.6   | 60   | 3.1543          | 1.0 |
| 3.2979        | 0.8   | 80   | 3.1295          | 1.0 |
| 3.1761        | 1.0   | 100  | 3.1033          | 1.0 |
| 3.1708        | 1.2   | 120  | 3.1019          | 1.0 |
| 3.1708        | 1.4   | 140  | 3.0894          | 1.0 |
| 3.0608        | 1.6   | 160  | 3.0664          | 1.0 |
| 3.0686        | 1.8   | 180  | 3.0616          | 1.0 |
| 3.0686        | 2.0   | 200  | 3.0622          | 1.0 |


### Framework versions

- Transformers 4.35.2
- Pytorch 2.3.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.2