---
license: apache-2.0
language:
- es
tags:
- whisper-event
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_11_0
- google/fleurs
- facebook/multilingual_librispeech
- facebook/voxpopuli
metrics:
- wer
model-index:
- name: openai/whisper-medium
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: mozilla-foundation/common_voice_11_0 es
      type: mozilla-foundation/common_voice_11_0
      config: es
      split: test
      args: es
    metrics:
    - name: Wer
      type: wer
      value: 6.346473676004366
    - name: Cer
      type: cer
      value: 2.1391
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: FLEURS ASR
      type: google/fleurs
      config: es_419
      split: test
      args: es
    metrics:
    - name: WER
      type: wer
      value: 4.0266
    - name: Cer
      type: cer
      value: 1.6631
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Multilingual LibriSpeech
      type: facebook/multilingual_librispeech
      config: spanish
      split: test
      args:
        language: es
    metrics:
    - name: WER
      type: wer
      value: 4.6644
    - name: Cer
      type: cer
      value: 1.7056
  - task:
      type: Automatic Speech Recognition
      name: speech-recognition
    dataset:
      name: VoxPopuli
      type: facebook/voxpopuli
      config: es
      split: test
      args:
        language: es
    metrics:
    - name: WER
      type: wer
      value: 8.3668
    - name: Cer
      type: cer
      value: 5.479
---

<!-- 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. -->

# openai/whisper-medium-mix-es

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the mozilla-foundation/common_voice_11_0, google/fleurs, facebook/multilingual_librispeech and facebook/voxpopuli datasets.
It achieves the following results on the evaluation set:
- Loss: 0.1344
- Wer: 6.3465

Using the [evaluation script](https://github.com/huggingface/community-events/blob/main/whisper-fine-tuning-event/run_eval_whisper_streaming.py) provided in the Whisper Sprint the model achieves these results on the test sets (WER):

- **google/fleurs: 4.0266 %**  
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="google/fleurs" --config="es_419" --device=0 --language="es")

- **facebook/multilingual_librispeech: 4.6644 %**  
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="facebook/multilingual_librispeech" --config="spanish" --device=0 --language="es")

- **facebook/voxpopuli: 8.3668 %**  
(python run_eval_whisper_streaming.py --model_id="deepdml/whisper-medium-mix-es" --dataset="facebook/voxpopuli" --config="es" --device=0 --language="es")


## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

Training data used:
- **mozilla-foundation/common_voice_11_0:** es, train+validation
- **google/fleurs:** es_419, train
- **facebook/multilingual_librispeech:** spanish, train
- **facebook/voxpopuli:** es, train

Evaluating over test split from mozilla-foundation/common_voice_11_0 dataset.

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- 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: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.266         | 0.2   | 1000 | 0.1657          | 8.0395 |
| 0.1394        | 0.4   | 2000 | 0.1539          | 7.3937 |
| 0.1316        | 0.6   | 3000 | 0.1452          | 6.9656 |
| 0.1165        | 0.8   | 4000 | 0.1392          | 6.5765 |
| 0.2816        | 1.0   | 5000 | 0.1344          | 6.3465 |


### Framework versions

- Transformers 4.26.0.dev0
- Pytorch 1.13.0+cu117
- Datasets 2.7.1.dev0
- Tokenizers 0.13.2