---
license: mit
base_model: facebook/w2v-bert-2.0
tags:
- automatic-speech-recognition
- librispeech_asr
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-bert-CV16-en-libri
  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. -->

# wav2vec2-bert-CV16-en-libri

This model is a fine-tuned version of [facebook/w2v-bert-2.0](https://huggingface.co/facebook/w2v-bert-2.0) on the LIBRISPEECH_ASR - CLEAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1331
- Wer: 0.0997
- Cer: 0.0264

## 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: 3e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- gradient_accumulation_steps: 2
- total_train_batch_size: 72
- total_eval_batch_size: 36
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 5.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Cer    | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:------:|:---------------:|:------:|
| 2.8812        | 0.63  | 250  | 1.0000 | 2.8923          | 1.0    |
| 1.2899        | 1.26  | 500  | 0.2563 | 1.1471          | 0.7030 |
| 0.5276        | 1.89  | 750  | 0.1127 | 0.4687          | 0.4114 |
| 0.3313        | 2.52  | 1000 | 0.0659 | 0.2870          | 0.2577 |
| 0.2089        | 3.16  | 1250 | 0.2079 | 0.1766          | 0.0445 |
| 0.1634        | 3.79  | 1500 | 0.1687 | 0.1411          | 0.0366 |
| 0.163         | 4.42  | 1750 | 0.1490 | 0.1163          | 0.0298 |


### Framework versions

- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0