---
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: base-asr-with-tpbs-cv5
  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. -->

# base-asr-with-tpbs-cv5

This model is a fine-tuned version of [Botnoi/base-asr-with-lm](https://huggingface.co/Botnoi/base-asr-with-lm) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.7171
- Wer: 0.3059
- Cer: 0.0883
- Clean Cer: 0.0817

## 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: 0.0001
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 100
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    | Cer    | Clean Cer |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:---------:|
| 0.1245        | 26.67 | 400  | 0.6505          | 0.3059 | 0.0887 | 0.0808    |
| 0.0431        | 53.33 | 800  | 0.6855          | 0.3049 | 0.0897 | 0.0826    |
| 0.0291        | 80.0  | 1200 | 0.7171          | 0.3059 | 0.0883 | 0.0817    |


### Framework versions

- Transformers 4.27.4
- Pytorch 1.13.1+cu117
- Datasets 2.11.0
- Tokenizers 0.13.2