README.md

metadata

license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
  - generated_from_trainer
datasets:
  - xtreme_s
metrics:
  - wer
model-index:
  - name: wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1
    results:
      - task:
          name: Automatic Speech Recognition
          type: automatic-speech-recognition
        dataset:
          name: xtreme_s
          type: xtreme_s
          config: fleurs.id_id
          split: test
          args: fleurs.id_id
        metrics:
          - name: Wer
            type: wer
            value: 1

wav2vec2-base-fleurs-CommonVoice-demo-google-colab-Ezra_William_Prod1

This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the xtreme_s dataset. It achieves the following results on the evaluation set:

• Loss: 2.1819
• Wer: 1.0

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: 0.0005
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 200
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
7.236	6.15	100	2.9095	1.0
2.8926	12.31	200	2.8601	1.0
2.871	18.46	300	2.8546	1.0
2.763	24.62	400	2.1819	1.0

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1