Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Demo Model Whisper Large
This model is a fine-tuned version of openai/whisper-large-v3 on the b-brave/speech_disorders_voice dataset. It achieves the following results on the evaluation set:
- Loss: 0.3430
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: 16
- eval_batch_size: 4
- 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_steps: 50
- num_epochs: 15
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.2968 | 1.7241 | 50 | 0.3434 |
0.2001 | 3.4483 | 100 | 0.3107 |
0.0827 | 5.1724 | 150 | 0.3031 |
0.0266 | 6.8966 | 200 | 0.3290 |
0.015 | 8.6207 | 250 | 0.3057 |
0.0083 | 10.3448 | 300 | 0.3294 |
0.0042 | 12.0690 | 350 | 0.3423 |
0.002 | 13.7931 | 400 | 0.3430 |
Framework versions
- PEFT 0.11.2.dev0
- Transformers 4.41.2
- Pytorch 2.3.1+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 120
Unable to determine this model’s pipeline type. Check the
docs
.