metadata
language:
- ab
license: apache-2.0
tags:
- automatic-speech-recognition
- mozilla-foundation/common_voice_7_0
- generated_from_trainer
datasets:
- common_voice
model-index:
- name: ''
results: []
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - AB dataset. It achieves the following results on the evaluation set:
- Loss: 0.5885
- Wer: 0.5899
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: 7.5e-05
- 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: 750
- num_epochs: 100.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 7.5798 | 13.64 | 300 | 3.4349 | 1.0 |
| 3.1252 | 27.27 | 600 | 3.0706 | 1.0 |
| 2.2546 | 40.91 | 900 | 0.8427 | 0.7763 |
| 0.7564 | 54.55 | 1200 | 0.6129 | 0.6376 |
| 0.5239 | 68.18 | 1500 | 0.5769 | 0.6037 |
| 0.438 | 81.82 | 1800 | 0.5938 | 0.5915 |
| 0.3945 | 95.45 | 2100 | 0.5869 | 0.5861 |
Framework versions
- Transformers 4.16.0.dev0
- Pytorch 1.10.1+cu102
- Datasets 1.17.1.dev0
- Tokenizers 0.11.0