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", device_map="auto")# 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", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 402 Bytes
52b498d 06d286f 52b498d 06d286f 52b498d 06d286f 52b498d | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | {
"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
} |