Automatic Speech Recognition
Transformers
PyTorch
hubert
abdusahmbzuai/arabic_speech_massive_300hrs
Generated from Trainer
Instructions to use abdusah/aradia-ctc-hubert-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use abdusah/aradia-ctc-hubert-ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="abdusah/aradia-ctc-hubert-ft")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("abdusah/aradia-ctc-hubert-ft") model = AutoModelForCTC.from_pretrained("abdusah/aradia-ctc-hubert-ft") - Notebooks
- Google Colab
- Kaggle
| { | |
| "epoch": 30.0, | |
| "eval_loss": 0.8535701632499695, | |
| "eval_runtime": 201.4101, | |
| "eval_samples": 4899, | |
| "eval_samples_per_second": 24.324, | |
| "eval_steps_per_second": 0.765, | |
| "eval_wer": 0.3736551873276748, | |
| "train_loss": 0.15137778351272363, | |
| "train_runtime": 18309.2993, | |
| "train_samples": 14730, | |
| "train_samples_per_second": 24.135, | |
| "train_steps_per_second": 0.377 | |
| } |