# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("GleamEyeBeast/test")
model = AutoModelForCTC.from_pretrained("GleamEyeBeast/test")Quick Links
test
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: 0.1761
- Wer: 0.2161
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: 32
- 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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 5.5828 | 4.0 | 500 | 3.0263 | 1.0 |
| 1.8657 | 8.0 | 1000 | 0.2213 | 0.2650 |
| 0.332 | 12.0 | 1500 | 0.2095 | 0.2413 |
| 0.2037 | 16.0 | 2000 | 0.1906 | 0.2222 |
| 0.1282 | 20.0 | 2500 | 0.1761 | 0.2161 |
Framework versions
- Transformers 4.11.3
- Pytorch 1.10.0+cu111
- Datasets 1.13.3
- Tokenizers 0.10.3
- Downloads last month
- 11
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="GleamEyeBeast/test")