---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- fsicoli/cv19-fleurs
metrics:
- wer
model-index:
- name: whisper-medium-pt-cv19-fleurs2-lr
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: fsicoli/cv19-fleurs default
      type: fsicoli/cv19-fleurs
      args: default
    metrics:
    - name: Wer
      type: wer
      value: 0.0953
---

<!-- 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. -->

# whisper-medium-pt-cv19-fleurs2-lr

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the fsicoli/cv19-fleurs default dataset in Portuguese.
It achieves the following results on the evaluation set:
- Loss: 0.2099
- Wer: 0.0953

## 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: 6.25e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 5000
- training_steps: 25000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch   | Step  | Validation Loss | Wer    |
|:-------------:|:-------:|:-----:|:---------------:|:------:|
| 0.0697        | 2.2883  | 5000  | 0.1620          | 0.1027 |
| 0.0272        | 4.5767  | 10000 | 0.1833          | 0.1038 |
| 0.0125        | 6.8650  | 15000 | 0.2036          | 0.0991 |
| 0.0057        | 9.1533  | 20000 | 0.2092          | 0.0983 |
| 0.0043        | 11.4416 | 25000 | 0.2099          | 0.0953 |


### Framework versions

- Transformers 4.45.0.dev0
- Pytorch 2.4.1
- Datasets 2.21.0
- Tokenizers 0.19.1