Whosper
Collection
Wolof ASR whisper based
•
5 items
•
Updated
Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whosper-turbo
This model is a fine-tuned version of openai/whisper-large-v3-turbo on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7594
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: 0.001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- 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_steps: 50
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0796 | 0.9998 | 2354 | 1.0086 |
| 0.9932 | 1.9998 | 4708 | 0.9251 |
| 0.9271 | 2.9998 | 7062 | 0.8672 |
| 0.8665 | 3.9998 | 9416 | 0.8163 |
| 0.784 | 4.9998 | 11770 | 0.7824 |
| 0.7456 | 5.9998 | 14124 | 0.7594 |
Framework versions
- PEFT 0.14.1.dev0
- Transformers 4.49.0.dev0
- Pytorch 2.5.1+cu124
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 25
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.