---
license: apache-2.0
base_model: pinot/wav2vec2-xls-r-300m-ja-phoneme_cv_14_3
tags:
- generated_from_trainer
datasets:
- audiofolder
metrics:
- wer
model-index:
- name: wav2vec2-xls-r-300m-ja-phoneme-cv-14_bench
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: audiofolder
      type: audiofolder
      config: default
      split: train
      args: default
    metrics:
    - name: Wer
      type: wer
      value: 0.17938553022794845
---

<!-- 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-xls-r-300m-ja-phoneme-cv-14_bench

This model is a fine-tuned version of [pinot/wav2vec2-xls-r-300m-ja-phoneme_cv_14_3](https://huggingface.co./pinot/wav2vec2-xls-r-300m-ja-phoneme_cv_14_3) on the audiofolder dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0125
- Wer: 0.1794

## 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: 16
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| No log        | 0.97  | 9    | 5.2662          | 0.2116 |
| No log        | 1.95  | 18   | 2.0125          | 0.1794 |


### Framework versions

- Transformers 4.31.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.3
- Tokenizers 0.13.3