---
language:
- ca
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
- hf-asr-leaderboard
datasets:
- mozilla-foundation/common_voice_11_0
metrics:
- wer
model-index:
- name: Whisper Small Catalan
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: mozilla-foundation/common_voice_11_0 ca
      type: mozilla-foundation/common_voice_11_0
      args: 'config: ml, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 8.569471791798646
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: google/fleurs ca
      type: google/fleurs
      args: 'config: ml, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 10.64
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: projecte-aina/parlament_parla clean
      type: projecte-aina/parlament_parla
      args: 'config: ml, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 19.0
---

<!-- 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 Small Catalan

This is an automatic speech recognition model that also does punctuation and casing. This model is for research only, **we do not recommend using this model on production environments**. See our [learnings](https://huggingface.co/softcatala/whisper-small-ca/blob/main/TRAINING.md) when training these models.

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the mozilla-foundation/common_voice_11_0 ca dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1980
- Wer: 8.5695

## 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: 1e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 20000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step  | Validation Loss | Wer     |
|:-------------:|:-----:|:-----:|:---------------:|:-------:|
| 0.2128        | 0.1   | 2000  | 0.2644          | 13.0303 |
| 0.1361        | 1.1   | 4000  | 0.2300          | 10.9568 |
| 0.0658        | 2.1   | 6000  | 0.2376          | 11.2810 |
| 0.102         | 3.09  | 8000  | 0.2156          | 9.8730  |
| 0.0706        | 4.09  | 10000 | 0.2126          | 9.6179  |
| 0.0428        | 5.09  | 12000 | 0.2178          | 9.3405  |
| 0.0503        | 6.09  | 14000 | 0.2109          | 9.1356  |
| 0.0778        | 7.08  | 16000 | 0.2058          | 9.2001  |
| 0.0082        | 8.08  | 18000 | 0.2173          | 8.9941  |
| 0.0994        | 9.08  | 20000 | 0.1980          | 8.5695  |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.10.0+cu102
- Datasets 2.7.1
- Tokenizers 0.13.2