metadata
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: shared_audio
results: []
shared_audio
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 19.5815
- Wer: 1.0
- Cer: 1.0
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: 3e-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: 20
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 62.6565 | 0.16 | 10 | 63.7309 | 1.0 | 2.9738 |
| 46.9251 | 0.32 | 20 | 54.7811 | 1.0 | 1.0 |
| 43.8044 | 0.48 | 30 | 32.9802 | 1.0 | 1.0 |
| 30.6358 | 0.64 | 40 | 26.5389 | 1.0 | 1.0 |
| 23.5351 | 0.8 | 50 | 23.3499 | 1.0 | 1.0 |
| 29.7649 | 0.96 | 60 | 21.5416 | 1.0 | 1.0 |
| 21.3599 | 1.12 | 70 | 20.5404 | 1.0 | 1.0 |
| 19.8412 | 1.28 | 80 | 19.8837 | 1.0 | 1.0 |
| 23.5039 | 1.44 | 90 | 19.5565 | 1.0 | 1.0 |
| 20.1719 | 1.6 | 100 | 19.4386 | 1.0 | 1.0 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2