Description
This model is a fine-tuned version of Rohan432/Augmented_on_normal. Rohan432/Augmented_on_normal is a finetuned version of bangla-speech-processing/BanglaASR on Bangla speech data.
Environment:
- Python version: 3.12.12
- PyTorch version: 2.8.0+cu126
- Librosa version: 0.10.1
- NumPy version: 1.26.4
Training Parameters:
- BATCH_SIZE = 4
- GRADIENT_ACCUMULATION_STEPS = 4
- LEARNING_RATE = 2e-5
- WARMUP_STEPS = 200
- NUM_TRAIN_EPOCHS = 8
- LOGGING_STEPS = 50
Validation Set Evaluation:
| Epoch | Training Loss | Validation Loss | WER | Normalized Levenshtein Similarity |
|---|---|---|---|---|
| 0 | 1.447600 | 1.466727 | 13.093923 | 90.565657 |
| 2 | 1.430200 | 1.469819 | 13.425414 | 90.040404 |
| 4 | 1.423800 | 1.461309 | 11.657459 | 91.272727 |
| 6 | 1.424000 | 1.458325 | 11.215470 | 91.545455 |
| 7 | 1.426100 | 1.457540 | 10.939227 | 91.848485 |
- Downloads last month
- 1