---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-large-960h
tags:
- generated_from_trainer
datasets:
- gigaspeech
metrics:
- wer
model-index:
- name: wav2vec_best
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: gigaspeech
      type: gigaspeech
      config: xs
      split: validation
      args: xs
    metrics:
    - name: Wer
      type: wer
      value: 0.2950402352212937
---

<!-- 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. -->

# wav2vec_best

This model is a fine-tuned version of [facebook/wav2vec2-large-960h](https://huggingface.co/facebook/wav2vec2-large-960h) on the gigaspeech dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7597
- Wer: 0.2950

## 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: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 1.5437        | 1.0    | 1174 | 0.7964          | 0.3166 |
| 1.4351        | 2.0    | 2348 | 0.7771          | 0.3061 |
| 0.6393        | 2.9978 | 3519 | 0.7597          | 0.2950 |


### Framework versions

- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1