# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("monideep2255/batch_size_8_50_epochs_base_model")
model = AutoModelForCTC.from_pretrained("monideep2255/batch_size_8_50_epochs_base_model")Quick Links
batch_size_8_50_epochs_base_model
This model is a fine-tuned version of facebook/wav2vec2-base-960h on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.6780
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.5872 | 6.67 | 200 | 3.6529 |
| 3.8231 | 13.33 | 400 | 3.7135 |
| 3.7257 | 20.0 | 600 | 3.7110 |
| 3.7043 | 26.67 | 800 | 3.6998 |
| 3.6979 | 33.33 | 1000 | 3.6782 |
| 3.6876 | 40.0 | 1200 | 3.6811 |
| 3.6897 | 46.67 | 1400 | 3.6780 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1
- Datasets 2.12.0
- Tokenizers 0.13.2
- Downloads last month
- 6
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="monideep2255/batch_size_8_50_epochs_base_model")