metadata
language:
- ha
license: apache-2.0
tags:
- automatic-speech-recognition
- mozilla-foundation/common_voice_8_0
- generated_from_trainer
- ha
- robust-speech-event
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_8_0 - HA dataset. It achieves the following results on the evaluation set:
- Loss: 0.4925
- Wer: 0.5714
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- 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: 2000
- num_epochs: 80.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 3.1674 | 8.33 | 500 | 3.0295 | 1.0 |
| 2.6987 | 16.66 | 1000 | 2.6878 | 1.0 |
| 1.3454 | 24.99 | 1500 | 0.6814 | 0.6981 |
| 1.1227 | 33.33 | 2000 | 0.5791 | 0.6513 |
| 0.9972 | 41.66 | 2500 | 0.5235 | 0.5718 |
| 0.9123 | 49.99 | 3000 | 0.5104 | 0.5633 |
| 0.836 | 58.33 | 3500 | 0.4927 | 0.5580 |
| 0.7725 | 66.66 | 4000 | 0.5078 | 0.5779 |
| 0.7297 | 74.99 | 4500 | 0.4939 | 0.5737 |
Framework versions
- Transformers 4.17.0.dev0
- Pytorch 1.10.2+cu113
- Datasets 1.18.4.dev0
- Tokenizers 0.11.0