metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
datasets:
- common_voice_13_0
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-300m-breton-colab
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice_13_0
type: common_voice_13_0
config: br
split: test
args: br
metrics:
- name: Wer
type: wer
value: 0.5302549302549302
wav2vec2-large-xls-r-300m-breton-colab
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0737
- Wer: 0.5303
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
- num_epochs: 30
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
2.8658 | 2.68 | 400 | 1.2395 | 0.8972 |
0.8219 | 5.37 | 800 | 0.9454 | 0.6731 |
0.4743 | 8.05 | 1200 | 0.8880 | 0.6181 |
0.3224 | 10.74 | 1600 | 0.9330 | 0.6148 |
0.2415 | 13.42 | 2000 | 1.0494 | 0.5889 |
0.1904 | 16.11 | 2400 | 1.0328 | 0.5469 |
0.152 | 18.79 | 2800 | 1.0771 | 0.5625 |
0.1231 | 21.48 | 3200 | 0.9980 | 0.5598 |
0.0993 | 24.16 | 3600 | 1.0351 | 0.5317 |
0.0788 | 26.85 | 4000 | 1.0560 | 0.5381 |
0.0653 | 29.53 | 4400 | 1.0737 | 0.5303 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3