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_0.9synth dataset. It achieves the following results on the evaluation set:
- Loss: 0.9568
- Wer: 40.6051
- Cer: 24.1709
- Clean Wer: 30.6324
- Clean Cer: 18.3212
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 | Validation Loss | Wer | Cer | Clean Wer | Clean Cer |
|---|---|---|---|---|---|---|---|
| 1.2498 | 1.0 | 1162 | 1.0305 | 44.9736 | 26.2819 | 34.8983 | 20.4239 |
| 1.1376 | 2.0 | 2324 | 0.9974 | 45.1705 | 26.6383 | 33.6258 | 20.2044 |
| 1.0073 | 3.0 | 3486 | 0.9692 | 41.3758 | 24.8708 | 31.3579 | 19.0546 |
| 0.9389 | 4.0 | 4648 | 0.9568 | 40.6051 | 24.1709 | 30.6324 | 18.3212 |
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
- 5
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for mizoru/whisper-large-ru-ORD_0.9_peft_wth_synth_0.1
Base model
openai/whisper-large-v2