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-welsh_10Epochen-colab
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice
type: common_voice
config: cy
split: test
args: cy
metrics:
- name: Wer
type: wer
value: 0.6030815223640336
wav2vec2-large-xls-r-300m-welsh_10Epochen-colab
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: 0.8080
- Wer: 0.6031
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.3225 | 2.5 | 300 | 2.8940 | 0.9996 |
| 1.4775 | 5.0 | 600 | 0.9166 | 0.7667 |
| 0.504 | 7.5 | 900 | 0.8496 | 0.6662 |
| 0.268 | 10.0 | 1200 | 0.8080 | 0.6031 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3