---
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-large-lv60
tags:
- automatic-speech-recognition
- librispeech_asr
- generated_from_trainer
datasets:
- librispeech_asr
metrics:
- wer
model-index:
- name: wav2vec2-librispeech-clean-100h-demo-dist
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: LIBRISPEECH_ASR - CLEAN
      type: librispeech_asr
      config: clean
      split: None
      args: 'Config: clean, Training split: train.100, Eval split: validation'
    metrics:
    - name: Wer
      type: wer
      value: 0.09198730662435542
---

<!-- 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. -->

# wav2vec2-librispeech-clean-100h-demo-dist

This model is a fine-tuned version of [facebook/wav2vec2-large-lv60](https://huggingface.co/facebook/wav2vec2-large-lv60) on the LIBRISPEECH_ASR - CLEAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0554
- Wer: 0.0920

## 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: 0.0003
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- 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: 500
- num_epochs: 3.0
- mixed_precision_training: Native AMP

### Training results



### Framework versions

- Transformers 4.53.1
- Pytorch 2.7.0+cu126
- Datasets 2.21.0
- Tokenizers 0.21.2