metadata
tags:
- generated_from_trainer
datasets:
- google/fleurs
metrics:
- wer
model-index:
- name: xls-r-fleurs_nl-run4
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: audiofolder
type: audiofolder
config: default
split: validation
args: default
metrics:
- name: Wer
type: wer
value: 0.46057420137484834
xls-r-fleurs_nl-run4
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the FLEURS (nl) dataset. It achieves the following results:
- Wer (Validation): 42.94%
- Wer (Test): 43.74%
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer (Train) |
|---|---|---|---|---|
| 0.1216 | 1.55 | 100 | 0.5803 | 0.4294 |
| 0.0775 | 3.1 | 200 | 0.6325 | 0.4420 |
| 0.0705 | 4.65 | 300 | 0.6473 | 0.4606 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu117
- Datasets 2.14.4
- Tokenizers 0.13.3