# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("pnparam/multi_stage_2")
model = AutoModelForCTC.from_pretrained("pnparam/multi_stage_2")Quick Links
multi_stage_2
This model is a fine-tuned version of pnparam/multi_stage_1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0510
- Wer: 1.3520
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 2.4404 | 1.36 | 500 | 0.1073 | 1.5140 |
| 0.1394 | 2.72 | 1000 | 0.1557 | 1.5888 |
| 0.1497 | 4.09 | 1500 | 0.1029 | 1.4735 |
| 0.0616 | 5.45 | 2000 | 0.0558 | 1.2118 |
| 0.0406 | 6.81 | 2500 | 0.0510 | 1.3520 |
Framework versions
- Transformers 4.17.0
- Pytorch 1.13.1+cu116
- Datasets 1.18.3
- Tokenizers 0.13.2
- Downloads last month
- 2
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="pnparam/multi_stage_2")