metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: wav2vec2-large-xls-r-300m-assamese
results: []
wav2vec2-large-xls-r-300m-assamese
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: 2.8161
- Wer: 0.9253
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: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.7373 | 66.67 | 400 | 2.8928 | 1.0 |
| 0.4283 | 133.33 | 800 | 2.3869 | 0.9715 |
| 0.0672 | 200.0 | 1200 | 2.6249 | 0.9431 |
| 0.0266 | 266.67 | 1600 | 2.7549 | 0.9490 |
| 0.0108 | 333.33 | 2000 | 2.7943 | 0.9229 |
| 0.0054 | 400.0 | 2400 | 2.8161 | 0.9253 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu113
- Datasets 1.13.3
- Tokenizers 0.10.3