Akan
Collection
Collection of Finetuned ASR models trained on the Asheshi financial dataset
•
51 items
•
Updated
wav2vec2-xls-r-asheshi-akan-1-hour
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: 3.0433
- 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: 32
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|---|---|---|---|---|---|
| 4.9628 | 29.4118 | 500 | 3.0433 | 1.0 | 1.0 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu121
- Datasets 2.17.0
- Tokenizers 0.21.0
- Downloads last month
- 1
Model tree for asr-africa/wav2vec2-xls-r-asheshi-akan-1-hour
Base model
facebook/wav2vec2-xls-r-300m