metadata
library_name: transformers
license: apache-2.0
base_model: facebook/wav2vec2-xls-r-300m
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: wav2vec2-xls-r-Wolof-1-hour-kallaama-dataset
results: []
wav2vec2-xls-r-Wolof-1-hour-kallaama-dataset
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5519
- Wer: 1.0
- Cer: 0.8960
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_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 3.9706 | 14.8148 | 200 | 2.9914 | 1.0 | 1.0 |
| 2.9733 | 29.6296 | 400 | 2.9697 | 1.0 | 1.0 |
| 2.851 | 44.4444 | 600 | 2.5519 | 1.0 | 0.8960 |
Framework versions
- Transformers 4.44.1
- Pytorch 2.1.0+cu118
- Datasets 2.17.0
- Tokenizers 0.19.1