README.md

---
base_model: ylacombe/w2v-bert-2.0
tags:
- generated_from_trainer
datasets:
- common_voice_6_1
metrics:
- wer
model-index:
- name: w2v-bert-2.0-turkish-colab-CV6.1
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: common_voice_6_1
      type: common_voice_6_1
      config: tr
      split: test
      args: tr
    metrics:
    - name: Wer
      type: wer
      value: 0.18384230415687877
---

<!-- 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. -->

# w2v-bert-2.0-turkish-colab-CV6.1

This model is a fine-tuned version of [ylacombe/w2v-bert-2.0](https://huggingface.co/ylacombe/w2v-bert-2.0) on the common_voice_6_1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1978
- Wer: 0.1838

## 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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 4.4016        | 0.92  | 100  | 2.4338          | 1.0428 |
| 0.5644        | 1.83  | 200  | 0.2224          | 0.1936 |
| 0.1692        | 2.75  | 300  | 0.1978          | 0.1838 |


### Framework versions

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