metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: ''
results: []
This model is a fine-tuned version of facebook/wav2vec2-xls-r-1b on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 1.2550
- Wer: 0.8842
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: 0.00015
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2000
- num_epochs: 10.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.0846 | 1.68 | 500 | 1.1641 | 0.8072 |
| 2.1201 | 3.35 | 1000 | 1.1776 | 0.8329 |
| 2.1972 | 5.03 | 1500 | 1.2632 | 0.8724 |
| 2.2643 | 6.71 | 2000 | 1.3723 | 0.8983 |
| 2.1649 | 8.39 | 2500 | 1.2550 | 0.8842 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu102
- Datasets 1.18.2.dev0
- Tokenizers 0.11.0