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_steps
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: 0.6465608465608466
wav2vec2-large-xls-r-300m-breton-colab_steps
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: 0.9111
- Wer: 0.6466
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: 300
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.7652 | 1.01 | 300 | 2.2099 | 0.9951 |
| 1.3954 | 2.02 | 600 | 1.1636 | 0.8122 |
| 0.8595 | 3.03 | 900 | 0.9715 | 0.7229 |
| 0.592 | 4.03 | 1200 | 0.9111 | 0.6466 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3