metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- common_voice
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-300m-eu
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice
type: common_voice
config: eu
split: test
args: eu
metrics:
- name: Wer
type: wer
value: 0.3081348220589389
wav2vec2-large-xls-r-300m-eu
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.2292
- Wer: 0.3081
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: 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: 5
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
3.5257 | 0.85 | 400 | 0.7206 | 0.8166 |
0.3916 | 1.7 | 800 | 0.3340 | 0.4837 |
0.2106 | 2.56 | 1200 | 0.2756 | 0.3994 |
0.1437 | 3.41 | 1600 | 0.2551 | 0.3410 |
0.0991 | 4.26 | 2000 | 0.2292 | 0.3081 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3