Tim Leiber
Upload tokenizer
1887286 verified
metadata
language:
  - fr
license: apache-2.0
tags:
  - generated_from_trainer
base_model: facebook/wav2vec2-large-xlsr-53
datasets:
  - mozilla-foundation/common_voice_17_0
metrics:
  - wer
model-index:
  - name: acoustic_model2_cv_17_fr_XLSR-53
    results:
      - task:
          type: automatic-speech-recognition
          name: Automatic Speech Recognition
        dataset:
          name: Common Voice 17
          type: mozilla-foundation/common_voice_17_0
          config: fr
          split: test
          args: fr
        metrics:
          - type: wer
            value: 0.9923249498169796
            name: Wer

acoustic_model2_cv_17_fr_XLSR-53

This model is a fine-tuned version of facebook/wav2vec2-large-xlsr-53 on the Common Voice 17 dataset. It achieves the following results on the evaluation set:

  • Loss: nan
  • Wer: 0.9923

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: 0.0003
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • 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: 500
  • training_steps: 1200
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Wer
16.0974 2.105 400 nan 0.9923
0.0 5.0958 800 nan 0.9923
0.0 8.0867 1200 nan 0.9923

Framework versions

  • Transformers 4.40.0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1