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: 2.9191
- Wer: 69.3030
- Cer: 36.7586
- Clean Wer: 38.4918
- Clean Cer: 23.1425
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 |
|---|---|---|---|---|---|---|---|
| 1.1554 | 1.0 | 613 | 2.6287 | 77.3618 | 52.7094 | 55.4565 | 41.9807 |
| 1.0513 | 2.0 | 1226 | 2.7804 | 73.4258 | 41.9948 | 46.7922 | 29.5494 |
| 0.9911 | 3.0 | 1839 | 2.7527 | 72.0139 | 39.5863 | 43.3650 | 26.3904 |
| 0.751 | 4.0 | 2452 | 2.9191 | 69.3030 | 36.7586 | 38.4918 | 23.1425 |
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
- 7
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for mizoru/whisper-large-ru-synth_0.1a_peft
Base model
openai/whisper-large-v2