Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
Whisper Large Ru ORD 0.9 Peft PEFT 4-bit Q DoRA - Mizoru
This model is a fine-tuned version of openai/whisper-large-v2 on the ORD_0.9 dataset. It achieves the following results on the evaluation set:
- Loss: 0.9677
- Wer: 40.6304
- Cer: 24.2408
- Clean Wer: 31.0879
- Clean Cer: 18.5515
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 50
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Cer | Clean Cer | Clean Wer | Validation Loss | Wer |
|---|---|---|---|---|---|---|---|
| 1.2054 | 1.0 | 550 | 26.2113 | 20.2832 | 33.6306 | 1.0018 | 43.5617 |
| 1.1705 | 2.0 | 1100 | 24.8572 | 19.2069 | 31.8977 | 0.9782 | 41.6030 |
| 1.0492 | 3.0 | 1650 | 24.3564 | 18.5862 | 31.1843 | 0.9598 | 40.9753 |
| 0.9011 | 4.0 | 2200 | 0.9677 | 40.6304 | 24.2408 | 31.0879 | 18.5515 |
Framework versions
- PEFT 0.12.0
- Transformers 4.41.0.dev0
- Pytorch 2.3.1
- Datasets 3.2.0
- Tokenizers 0.19.1
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
HF Inference deployability: The model has no pipeline_tag.
Model tree for mizoru/whisper-large-ORD_0.9_peft_0.3
Base model
openai/whisper-large-v2