README.md

metadata

license: cc-by-nc-4.0
base_model: facebook/mms-1b-FL102
tags:
  - generated_from_trainer
datasets:
  - audiofolder
metrics:
  - wer
model-index:
  - name: wav2vec2-large-mms-4-spanish-colab
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: audiofolder
          type: audiofolder
          config: default
          split: test
          args: default
        metrics:
          - name: Wer
            type: wer
            value: 0.6762402088772846

wav2vec2-large-mms-4-spanish-colab

This model is a fine-tuned version of facebook/mms-1b-FL102 on the audiofolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.5208
• Wer: 0.6762

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: 0.001
• train_batch_size: 6
• 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: 100
• num_epochs: 12

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
4.1561	3.45	100	1.7298	0.7154
1.4874	6.9	200	1.5586	0.6789
1.338	10.34	300	1.5208	0.6762

Framework versions

• Transformers 4.36.0.dev0
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0