README.md

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_model0_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: 0.46428149722517414
            name: Wer

acoustic_model0_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: 0.5171
• Wer: 0.4643

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: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer
3.0475	2.084	400	2.9894	0.9949
1.2413	5.0767	800	0.6745	0.5958
0.5812	8.0693	1200	0.5171	0.4643

Framework versions

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