Fula
Collection
Collection of finetuned ASR models trained on increasing proportions of Fula language data.
•
18 items
•
Updated
wav2vec2-xlsr-fula-google-fleurs-1-hour
This model is a fine-tuned version of facebook/wav2vec2-xls-r-300m on the fleurs dataset. It achieves the following results on the evaluation set:
- Loss: 2.9868
- 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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 7.4091 | 61.54 | 200 | 2.9868 | 1.0 | 1.0 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu118
- Datasets 2.17.0
- Tokenizers 0.15.2
- Downloads last month
- 14
Model tree for asr-africa/wav2vec2-xlsr-fula-google-fleurs-1-hour-plus-lm
Base model
facebook/wav2vec2-xls-r-300m