metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-large-xls-r-300m-en
results: []
wav2vec2-large-xls-r-300m-en
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8281
- Wer: 0.5698
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: 10
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.9669 | 0.9971 | 171 | 3.0636 | 1.0 |
| 3.0225 | 2.0 | 343 | 2.9644 | 1.0 |
| 2.9628 | 2.9971 | 514 | 1.9962 | 1.0301 |
| 1.5081 | 4.0 | 686 | 1.1949 | 0.7784 |
| 1.0398 | 4.9971 | 857 | 0.9907 | 0.6939 |
| 0.8111 | 6.0 | 1029 | 0.8605 | 0.5979 |
| 0.5514 | 6.9796 | 1197 | 0.8281 | 0.5698 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1