metadata
license: apache-2.0
language:
- gn
tags:
- generated_from_trainer
- mozilla-foundation/common_voice_8_0
- robust-speech-event
datasets:
- common_voice
- mozilla-foundation/common_voice_8_0
model-index:
- name: wav2vec2-base-gn-demo
results: []
wav2vec2-base-gn-demo
This model is a fine-tuned version of azuur/wav2vec2-base-gn-demo on the common_voice dataset. It achieves the following results on the evaluation set:
- Loss: 1.1139
- Wer: 0.7835
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: 0.0002
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 300
- num_epochs: 55
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Wer |
---|---|---|---|---|
0.1803 | 13.16 | 500 | 1.2114 | 0.8415 |
0.1343 | 26.32 | 1000 | 1.1728 | 0.8155 |
0.0986 | 39.47 | 1500 | 1.1220 | 0.8293 |
0.0581 | 52.63 | 2000 | 1.1139 | 0.7835 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.18.3
- Tokenizers 0.10.3