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-euskera-colab
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: 0.28292759459247446
wav2vec2-large-xls-r-300m-euskera-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: 0.2281
- Wer: 0.2829
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: 4
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.6474 | 0.43 | 400 | 0.8974 | 0.9025 |
| 0.4849 | 0.85 | 800 | 0.4653 | 0.6314 |
| 0.2924 | 1.28 | 1200 | 0.3726 | 0.5294 |
| 0.2392 | 1.7 | 1600 | 0.3203 | 0.4461 |
| 0.1957 | 2.13 | 2000 | 0.2932 | 0.4053 |
| 0.1592 | 2.56 | 2400 | 0.2767 | 0.3760 |
| 0.1442 | 2.98 | 2800 | 0.2605 | 0.3635 |
| 0.1166 | 3.41 | 3200 | 0.2662 | 0.3415 |
| 0.1064 | 3.84 | 3600 | 0.2576 | 0.3409 |
| 0.0906 | 4.26 | 4000 | 0.2567 | 0.3234 |
| 0.0818 | 4.69 | 4400 | 0.2472 | 0.3063 |
| 0.0701 | 5.11 | 4800 | 0.2440 | 0.2951 |
| 0.0595 | 5.54 | 5200 | 0.2321 | 0.2810 |
| 0.0566 | 5.97 | 5600 | 0.2281 | 0.2829 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3