Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-large3-mon
This model is a fine-tuned version of openai/whisper-large-v3 on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.4062
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: 18
- eval_batch_size: 18
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 2.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.103 | 0.5882 | 100 | 0.7301 |
| 0.5508 | 1.1765 | 200 | 0.5630 |
| 0.4061 | 1.7647 | 300 | 0.4062 |
Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for Badral/whisper-large3-mon
Base model
openai/whisper-large-v3