metadata
language:
- fr
license: apache-2.0
base_model: facebook/wav2vec2-large-xlsr-53
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: acoustic_model0_cv_17_fr_XLSR-53
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: Common Voice 17
type: mozilla-foundation/common_voice_17_0
config: fr
split: test
args: fr
metrics:
- name: Wer
type: wer
value: 0.533356948872358
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: 0.5859
- Wer: 0.5334
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 |
---|---|---|---|---|
7.2 | 2.105 | 400 | 3.0327 | 0.9949 |
2.8531 | 5.0958 | 800 | 1.5473 | 0.9133 |
1.0966 | 8.0867 | 1200 | 0.5859 | 0.5334 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1